CN107393000A - Image processing method, device, server and computer-readable recording medium - Google Patents
Image processing method, device, server and computer-readable recording medium Download PDFInfo
- Publication number
- CN107393000A CN107393000A CN201710737532.7A CN201710737532A CN107393000A CN 107393000 A CN107393000 A CN 107393000A CN 201710737532 A CN201710737532 A CN 201710737532A CN 107393000 A CN107393000 A CN 107393000A
- Authority
- CN
- China
- Prior art keywords
- target object
- images
- image
- models
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 100
- 238000009877 rendering Methods 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 description 18
- 230000000694 effects Effects 0.000 description 13
- 230000000875 corresponding effect Effects 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000007787 solid Substances 0.000 description 4
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
- G06T15/205—Image-based rendering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a kind of image processing method, device, server and computer-readable recording medium.The above method, including：The image processing requests that mobile terminal is sent are received, described image processing request includes pending 2D images；Extract the characteristics of image of the 2D images；Similarity mode calculating is carried out to described image feature in database, identifies the target object of the 2D images, and obtain the physical parameter matched with the target object；The 3D models of the target object are built according to the physical parameter, and the target object of the 2D images is replaced with into the 3D models, obtain 3D rendering；The 3D rendering is returned into the mobile terminal.Above-mentioned image processing method, device, server and computer-readable recording medium, 2D images can be converted into 3D rendering automatically, enabling image-watching, person perceives more image informations, and simple and efficient.
Description
Technical field
The application is related to field of computer technology, more particularly to a kind of image processing method, device, server and calculating
Machine readable storage medium storing program for executing.
Background technology
The image that imaging device (such as camera, video camera etc.) shooting obtains is generally with 2D's (2Dimensions, 2 dimensions)
Form is presented, and 2D images are also referred to as plane picture, and 2D images may lose the information of some subjects.And 3D
(3Dimensions, 3-dimensional) image can perceive beholder and experience the depth of subject, so as to obtain more quilt
Take the photograph object information.Traditional 2D images turn 3D rendering, it is necessary to which user shifts to the region of 2D images manually, so as to create not
It is cumbersome with the picture construction 3D rendering at visual angle.
The content of the invention
The embodiment of the present application provides a kind of image processing method, device, server and computer-readable recording medium, can be with
Automatically 2D images are converted into 3D rendering, enabling image-watching, person perceives more image informations, and simple and efficient.
A kind of image processing method, including：
The image processing requests that mobile terminal is sent are received, described image processing request includes pending 2D images；
Extract the characteristics of image of the 2D images；
Similarity mode calculating is carried out to described image feature in database, identifies the target object of the 2D images,
And obtain the physical parameter matched with the target object；
The 3D models of the target object are built according to the physical parameter, and the target object of the 2D images is replaced
For the 3D models, 3D rendering is obtained；
The 3D rendering is returned into the mobile terminal.
In one of the embodiments, the physical parameter includes form parameter, size parameter and parametric texture；
The 3D models that the target object is built according to the physical parameter, including：
Build the 3D grid models of the target object in proportion according to the form parameter and size parameter；
The 3D grid models are rendered according to the parametric texture.
In one of the embodiments, the characteristics of image of the extraction 2D images, including：
The 2D images are divided into foreground area and the background area in addition to the foreground area, and respectively described in extraction
Foreground area and the characteristics of image of background area, the foreground area include target object.
In one of the embodiments, described image processing request includes handling type, and the processing type includes panorama
Processing；
After the 3D models that the target object is built according to the physical parameter, methods described also includes：
Similarity mode calculating is carried out to the characteristics of image of the background area in the database, identifies the 2D figures
The image scene of picture；
The multi-angle scene image with described image scene matching is obtained from the database；
According to the multi-angle scene image synthesize 3D panoramic scene images, and by the 3D panoramic scenes image with it is described
The 3D Model Fusions of target object, obtain 3D rendering.
In one of the embodiments, the processing type includes virtual scene processing；
After the 3D models that the target object is built according to the physical parameter, methods described also includes：
Destination virtual scene is determined according to the processing type, and obtains the virtual field with the destination virtual scene matching
Scape data；
3D virtual scene images are built according to the virtual scene data；
By the 3D virtual scenes image and the 3D Model Fusions of the target object, 3D rendering is obtained.
In one of the embodiments, the 3D models that the target object is built according to the physical parameter, including：
When the virtual scene packet contain with the first of the destination virtual scene matching dress up parameter when, according to institute
State physical parameter and the described first parameter of dressing up builds the 3D models of the target object.
In one of the embodiments, the processing type is dressed up processing including target object；
After the physical parameter for obtaining and being matched with the target object, methods described also includes：
Classification of dressing up is determined according to the processing type；
Corresponding with the physical parameter second is chosen in the classification of dressing up to dress up parameter；
The 3D models of the target object are built according to the parameter of dressing up of the physical parameter and second.
A kind of image processing apparatus, including：
Receiving module, for receiving the image processing requests of mobile terminal transmission, described image processing request includes waiting to locate
The 2D images of reason；
Extraction module, for extracting the characteristics of image of the 2D images；
Identification module, for carrying out similarity mode calculating to described image feature in database, identify the 2D figures
The target object of picture, and obtain the physical parameter matched with the target object；
Module is built, for building the 3D models of the target object according to the physical parameter, and by the 2D images
Target object replace with the 3D models, obtain 3D rendering；
Sending module, for the 3D rendering to be returned into the mobile terminal.
A kind of server, including memory and processor, computer program, the computer are stored in the memory
When programmed instruction is by the computing device so that the processor realizes method as described above.
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
Method as described above is realized during row.
Brief description of the drawings
Fig. 1 is the application scenario diagram of image processing method in one embodiment；
Fig. 2 is the block diagram of server in one embodiment；
Fig. 3 is the schematic flow sheet of image processing method in one embodiment；
Fig. 4 is the schematic flow sheet of the 3D models for the target object that 2D images are built in one embodiment；
Fig. 5 is the schematic flow sheet that 2D images are converted to 3D rendering in one embodiment；
Fig. 6 is the schematic flow sheet that 2D images are converted to 3D rendering in another embodiment；
Fig. 7 is the schematic flow sheet that 2D images are converted to 3D rendering in another embodiment；
Fig. 8 is the block diagram of image processing apparatus in one embodiment.
Embodiment
In order that the object, technical solution and advantage of the application are more clearly understood, it is right below in conjunction with drawings and Examples
The application is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the application, not
For limiting the application.
It is appreciated that term " first " used in this application, " second " etc. can be used to describe various elements herein,
But these elements should not be limited by these terms.These terms are only used for distinguishing first element and another element.Citing comes
Say, in the case where not departing from scope of the present application, the first client can be referred to as the second client, and similarly, can incite somebody to action
Second client is referred to as the first client.First client and the second client both clients, but it is not same visitor
Family end.
Fig. 1 is the application scenario diagram of image processing method in one embodiment.As shown in figure 1, mobile terminal 10 can pass through
Network and server 20, which are established, to be communicated to connect, wherein, server 20 can be single server or by multiple services
The server cluster of device composition, or a certain server in server cluster.Mobile terminal 10 is sent to server 20 schemes
As processing request.Server 20 receives the image processing requests that mobile terminal 10 is sent, and image processing requests include pending
2D images, extract the characteristics of image of 2D images.Server 20 carries out similarity mode in database to the characteristics of image of extraction
Calculate, identify the target object of 2D images, and obtain the physical parameter matched with target object.Server 20 is according to physical parameter
The 3D models of target object are built, and the target object of 2D images is replaced with into 3D models, obtain 3D rendering, and 3D rendering is returned
Back to mobile terminal 10.The 3D rendering that mobile terminal 10 can return to server 20 is shown.
Fig. 2 is the block diagram of server 20 in one embodiment.As shown in Fig. 2 the server 20 includes passing through system bus
Processor, non-volatile memory medium, built-in storage and the network interface of connection.Wherein, the non-volatile of the server 20 is deposited
Storage media is stored with operating system, database and computer program, and view data etc. is stored with database, the computer program
For realizing a kind of image processing method suitable for server provided in the embodiment of the present application.The processor of the server 20
For providing calculating and control ability, the operation of whole server 20 is supported.The built-in storage of the server 20 is non-volatile
Operating system and computer program in storage medium provide the running environment of cache.The network interface of the server 20 is used
According to this with outside mobile terminal communicated by network connection, such as receive mobile terminal send image processing requests, to
Mobile terminal returns to 3D rendering etc..Server 20 can with independent server either multiple server groups into server set
Group realizes.It will be understood by those skilled in the art that the structure shown in Fig. 2, the only part related to application scheme
The block diagram of structure, the restriction for the server 20 being applied thereon to application scheme is not formed, specifically server 20 can
With including than more or less parts shown in figure, either combining some parts or being arranged with different parts.
As shown in figure 3, in one embodiment, there is provided a kind of image processing method, comprise the following steps：
Step 310, the image processing requests that mobile terminal is sent are received, image processing requests, which include pending 2D, schemes
Picture.
The 2D images that mobile terminal will can be gathered by imaging first-class imaging device, or the hair such as 2D images prestored
Server is delivered to, the 2D images are converted into 3D rendering by server, in the present embodiment, 2D images can pass through camera
Planar picture of collection etc..Mobile terminal can send image processing requests to server, can include and need in image processing requests
The 2D images of processing, the image information of 2D images, and information of mobile terminal etc..Image information may include that image identification etc. is believed
Breath, wherein, image identification can be the letter that image name, picture number etc. can be used for unique mark image in the terminal
Breath；Information of mobile terminal may include the information such as the mark of mobile terminal, account, wherein, the mark of mobile terminal can be mobile
MAC (Media Access Control, media access control layer) of terminal etc..
Step 320, the characteristics of image of 2D images is extracted.
After server receives the image processing requests that mobile terminal is sent, image processing requests can be parsed, and obtain image
The pending 2D images included in processing request.Server can extract the characteristics of image of 2D images.Characteristics of image may include shape
Shape feature, space characteristics, edge feature, color characteristic and textural characteristics etc., wherein, shape facility refers to local in 2D images
Shape, space characteristics refer to the mutual locus or relative direction between multiple regions for being split in 2D images
Relation, edge feature refer to forming boundary pixel between two regions etc. in 2D images, and color characteristic and textural characteristics are equal
It is a kind of global characteristics, the surface nature available for the object corresponding to description image or image-region.For same 2D images
In different types of characteristics of image, server can be extracted in different ways, for example, color characteristic can be schemed by 2D
The color histogram of picture is extracted, and shape facility can be by building gradient of image and gray scale direction matrix, and therefrom obtains 2D figures
The boundary characteristic description of picture is extracted etc., is not restricted herein.
Step 330, similarity mode calculating is carried out to characteristics of image in database, identifies the target object of 2D images,
And obtain the physical parameter matched with target object.
Server can be handled the 2D images that mobile terminal uploads based on big data, is turned 2D images using big data
It is changed to 3D rendering.In one embodiment, server can be divided characteristics of image by the object identification model pre-established
Analysis, and the target object of 2D images is identified, wherein, target object refers to the main body of 2D images, can be people, animal, plant
Or other do not have lived object etc..The object identification model can enter previously according to the substantial amounts of view data stored in database
Row structure, sample that can be using the substantial amounts of view data stored in database as object identification model, to being wrapped in each sample
The characteristic point of the target object contained is marked, the characteristic point of mark can be used for the shape of target object in description sample, size,
The feature such as space and border, study is trained to the great amount of samples of mark, can obtain object identification model, the object identification mould
The mapping relations of characteristics of image and characteristic point shape are established in type.Object identification model can be first according to characteristics of image to 2D images
Target object carry out preliminary rude classification, determine the major class belonging to target object, wherein, major class may include people, animal, plant
Thing, building, daily necessities etc., but not limited to this.After server obtains the rude classification of the target object of 2D images, it can pass through again
The classification that object identification model is refined, for example, insects, flying bird, mammality etc. can be divided into again under animal category, then look for
To the characteristic point shape for possessing mapping relations with described image feature, so as to identify to obtain the target object of 2D images.
In one embodiment, server can also be encoded the characteristics of image of the 2D images of extraction, and will be substantial amounts of
Image is stored in database after being encoded, a large amount of using being stored in the encoded radio and database of the characteristics of image of extraction
Image encoded radio carry out global or local similarity mode calculate, and in retention data storehouse similarity be more than threshold value figure
Picture, further screened.The image that server will can screen to obtain in the characteristics of image and database of the 2D images of extraction
Compared one by one, and determine the target object of 2D images.
Server identifies the target object of 2D images, can obtain the physical parameter matched with the target object, physical parameter
The physical features such as the form and dimension available for description target object, wherein, physical parameter may include form parameter, size parameter
And parametric texture etc., if for example, target object is cup, physical parameter can be the shape of cup, height, width, caliber size and
The data such as the pattern texture on cup shell, if target object is people, physical parameter can be the height of people, shoulder breadth, waistline, face
Type etc..In one embodiment, the physical parameter matched with target object, server identification 2D can be previously stored with database
After the target object of image, the physical parameter matched with the target object can be directly obtained from database.
In one embodiment, server also can obtain the physical parameter of target object from 2D images, and combine data
The physical parameter stored in storehouse, the common 3D models for building target object.For example, the target object of server identification 2D images is
Cup, server can obtain the pattern texture on shape, height, width, caliber size and the cup shell of the cup from database
Etc. data, the physical parameters such as the angles of the cup can be also obtained from 2D images.
Step 340, the 3D models of target object are built according to physical parameter, and the target object of 2D images is replaced with into 3D
Model, obtain 3D rendering.
The 2D images that mobile terminal uploads can be converted to 3D rendering by server, and the mode of conversion can be a variety of, example
Such as, from plane conversion beholder can be allowed to perceive the 3D models of Object Depth the target object of 2D images, can also incited somebody to action
The photographed scene of 2D images is converted to 3D outdoor scenes etc., enables a viewer to carry out 360 degree of panorama observations.
In one embodiment, server can build object according to the physical parameter matched in 2D images with target object
The 3D models of body, wherein, 3D models can be by summit, and the line, the polygonal figures that are made up of summit are described.Server
Loading processing can will be carried out to physical parameter by graphics processor, physical parameter is converted into multiple summits of structure 3D models
Information, wherein, vertex information may include the apex coordinate on each summit, color, texture etc., so as to form the 3D moulds of target object
Type.In one embodiment, server can determine that the positional information of target object in 2D images, and according to the positional information by 2D
The target object of image replaces with the 3D models of structure, obtains 3D rendering.
Step 350,3D rendering is returned into mobile terminal.
3D rendering is returned to mobile terminal by server according to the mark of mobile terminal.Mobile terminal can be carried out to 3D rendering
Displaying, in one embodiment, user can pass through the displaying of the operational control 3D rendering such as touch-control.For example, mobile terminal can basis
3D models in the rotary display 3D rendering such as gesture operation track of user, mobile terminal can also be sensed according to gravity sensor
Change direction, and 3D models in change direction rotary display 3D rendering, but not limited to this.
In the present embodiment, similarity mode calculating can be carried out to the characteristics of image of the 2D images of extraction in database,
The target object of 2D images is identified, and the physical parameter matched according to target object builds the 3D models of target object, can be based on
2D images are converted into 3D rendering by big data automatically, and enabling image-watching, person perceives more image informations, simple and efficient.It is and logical
The target object of big data identification 2D images is crossed, the physical parameter matched with target object is obtained, more targets can be obtained
Object information, makes that the 3D models of structure are truer, possess more details.
As shown in figure 4, in one embodiment, step builds the 3D models of target object according to physical parameter, including with
Lower step：
Step 402, the 3D grid models of target object are built in proportion according to form parameter and size parameter.
Physical parameter can be used for the physical features such as the form and dimension of description target object, wherein, physical parameter may include
Form parameter, size parameter and parametric texture etc..Server can will carry out loading processing by graphics processor to physical parameter,
And build the 3D grid models of target object in proportion according to form parameter and size parameter etc., make the 3D of the target object of structure
Grid model presses close to the size and shape of target object in 2D images.Physical parameter can be converted into structure 3D models by server
Multiple vertex informations, and each summit is combined to different geometric graphic elements, 3D grid models are built according to the geometric graphic element of combination,
Wherein, geometric graphic element may include point, line and polygon etc..
Step 404,3D grid models are rendered according to parametric texture.
Server can colour according to parametric texture, color parameter etc. to 3D grid models, and render what is drawn
3D models, server can be adjusted according to the positional information of target object in 2D images with shape contour to 3D models, and will
The target object of 2D images replaces with the 3D models, obtains 3D rendering.
In one embodiment, server can also obtain the target object image of multi-angle from 2D images, and will obtain
The target object image of multi-angle be divided into left-eye image and eye image, wherein, left-eye image refers to the left side according to people
The image of eye collection, eye image refer to the image gathered according to the right eye of people, can be further according to left-eye image and eye image
Three-dimensional 3D models are generated, are not limited in aforesaid way.
In the present embodiment, the 3D models of target object in 2D images can be generated based on big data, by the 2D images of plane
The 3D rendering of solid is converted into, enabling image-watching, person perceives more image informations, and simple and efficient.
In one embodiment, the characteristics of image of step 320 extraction 2D images, including：2D images are divided into foreground zone
Domain and the background area in addition to foreground area, and the characteristics of image of foreground area and background area, foreground area bag are extracted respectively
Include target object.
, can be first to 2D images after the image processing requests that server is sent according to mobile terminal obtain pending 2D images
Region division is carried out, 2D images are divided into the foreground area comprising target object, and the background area in addition to foreground area.
Foreground area can be default shape, such as rectangle etc., can first determine the approximate location in 2D images residing for target object, and
The foreground area of preset shape is chosen according to the approximate location, divides foreground area and the background area of 2D images.Server can
The characteristics of image of foreground area and background area is extracted respectively, and only the characteristics of image of foreground area can be carried out in database
Similarity mode calculates, so as to identify the target object of 2D images.
In the present embodiment, 2D images are divided into foreground area and background area, can be only special to the image of foreground area
Sign is analyzed, and identifies the target object of 2D images, recognition result can be made more accurate, reduces noise.
As shown in figure 5, in one embodiment, after step builds the 3D models of target object according to physical parameter,
Above-mentioned image processing method is further comprising the steps of：
Step 502, similarity mode calculating is carried out to the characteristics of image of background area in database, identification 2D images
Image scene.
In one embodiment, user can select to need the 2D images handled on mobile terminals, and select correspondingly
Processing type, wherein, processing type may include it is a variety of, for example, only carrying out 3D processing to the target objects of 2D images, only to 2D
The background of image carries out 3D processing, or the target object and background of 2D images are handled etc..In the present embodiment, locate
Reason type can panorama processing, virtual scene processing, target object dress up processing and single goal object turn 3D processing etc., wherein, entirely
Scape processing refers to that by the background of 2D images be 3D outdoor scenes from 2D plane conversions, and virtual scene processing is referred to the back of the body of 2D images
Scape is converted to virtual 3D backgrounds from outdoor scene, and target object processing of dressing up is referred to the target object of 2D images from plane conversion
For solid 3D models while, 3D models are dressed up, single goal object turns 3D processing and referred to the mesh of 2D images only
Mark 3D model of the object from plane conversion for solid.It is to be appreciated that by 2D images be converted to 3D rendering also have it is a lot of other
Processing mode, it is not limited to that.
In one embodiment, after server receives the image processing requests that mobile terminal is sent, processing type can be obtained,
When it is that panorama is handled to handle type, server can be based on big data and carry out scene Recognition to 2D images.In one embodiment,
Server can be analyzed the characteristics of image of the background area of 2D images by the scene Recognition model pre-established, identify 2D
The image scene of image, image scene may include the places of 2D image takings, Background Buildings, landscape environment etc..In an implementation
In example, also the characteristics of image of the background area of 2D images and the characteristics of image of the great amount of images stored in database can be subjected to phase
Like degree matching primitives, therefrom choose similarity and be more than the image of threshold value, and determine the image scene of 2D images.
Step 504, the multi-angle scene image matched with image scene is obtained from database.
Server can according to the image scene of the 2D images of identification, obtained from database matched with image scene it is polygonal
Spend scene image.In one embodiment, when mobile terminal is to server transmission image processing requests, can be sent out simultaneously to server
, can profit after sending the collection address information of 2D images, server to obtain the collection address information of 2D images according to image processing requests
Multiple multi-angled shooting images corresponding with the collection address information are chosen from database with the collection address information of 2D images, and
Choose what multiple were matched with the image scene of 2D images from multiple multi-angled shooting images corresponding with the collection address information
Multi-angle scene image.
Step 506,3D panoramic scene images are synthesized according to multi-angle scene image, and by 3D panoramic scenes image and target
The 3D Model Fusions of object, obtain 3D rendering.
The multi-angle scene image that server can match according to multiple of selection with image scene, synthesize 3D panoramic scene figures
3D outdoor scene effects can be presented in picture, the 3D panoramic scenes image.Server can determine that the scene border of every scene image of selection,
And multiple multi-angle scene images are aligned according to scene border, so as to synthesize 3D panoramic scene images.In an implementation
In example, the 3D models of target object and 3D panoramic scene image co-registrations can be obtained 3D rendering, and 3D rendering is returned by server
To mobile terminal.User can pass through the displaying of the operational control 3D rendering such as touch-control.For example, mobile terminal can be according to the gesture of user
The draggings such as operation trace are up and down or zoom shows 3D panoramic scenes of 3D rendering etc..
In one embodiment, server only can also be handled the background area of 2D images, by the background of 2D images
3D panoramic scenes are converted to, 3D conversions are not carried out to target object.
In the present embodiment, 2D images can be converted to the 3D rendering for including 3D panoramic scenes, the person that enables image-watching
More image informations are perceived, improve the visual display effect of image.
As shown in fig. 6, in one embodiment, after step builds the 3D models of target object according to physical parameter,
Above-mentioned image processing method is further comprising the steps of：
Step 602, destination virtual scene is determined according to processing type, and obtains the virtual field with destination virtual scene matching
Scape data.
In one embodiment, after server receives the image processing requests that mobile terminal is sent, processing type can be obtained,
When it is that virtual scene is handled to handle type, destination virtual scene can be obtained, wherein, virtual scene may refer to the field of unreality
Scape, user can select required destination virtual scene in mobile terminal, replace the background of 2D images, for example, universe virtual scene,
Seabed virtual scene etc., but not limited to this.Database can be previously stored with the virtual scene data of substantial amounts of different virtual scenes,
Server can be obtained from database and the virtual scene data of destination virtual scene matching, wherein, virtual scene data can wrap
Include the vertex information for building 3D virtual scene images.
Step 604,3D virtual scene images are built according to virtual scene data.
Server can build 3D virtual scene images according to the virtual scene data of acquisition, further, can be according to virtual
The multiple vertex informations included in contextual data, such as the information such as apex coordinate, color, texture, build 3D virtual scene images.
Step 606, by 3D virtual scenes image and the 3D Model Fusions of target object, 3D rendering is obtained.
3D virtual scenes image and the 3D Model Fusions of target object can be obtained 3D rendering by server.In an implementation
Example in, if virtual scene packet contain with the first of destination virtual scene matching dress up parameter when, can be according to target object
Physical parameter and the first parameter of dressing up build the 3D models of target object jointly, wherein, the first parameter of dressing up may include and target
The dress ornament of virtual scene matching, hair style, dressing etc..Mesh is built according to the parameter of dressing up of the physical parameter of target object and first jointly
The 3D models of object are marked, the 3D models of the target object of structure is more met destination virtual scene.In one embodiment, also may be used
After adjusting 3D models and 3D virtual scene image co-registrations according to the characteristics of destination virtual scene, display location in the 3 d image and
Show posture etc..
For example, the destination virtual scene that server obtains according to image processing requests is moon virtual scene, then can basis
The virtual scene data structure virtual moon scene images of 3D matched with moon virtual scene, wherein, virtual scene packet contains
There is first to dress up parameter, first parameter of dressing up can be used for structure to wear the 3D of space suit effect is presented.Server can according to
The first of moon virtual scene matching is dressed up the physical parameter of the people included in parameter and 2D images, common to build people and wear space
The 3D models of clothes, and after the 3D models for adjusting people merge with the virtual moon scene images of 3D, display location in the 3 d image, make
The 3D rendering can show people and wear the effect that space suit is swum in the virtual moon of 3D when mobile terminal is presented.
In the present embodiment, 2D images can be converted to the 3D rendering for including 3D virtual scenes, the person that enables image-watching
More image informations are perceived, improve the visual display effect of image.
As shown in fig. 7, in one embodiment, after step builds the 3D models of target object according to physical parameter,
Above-mentioned image processing method is further comprising the steps of：
Step 702, classification of dressing up is determined according to processing type.
After server receives the image processing requests that mobile terminal is sent, processing type can be obtained, when processing type is mesh
Mark object dress up processing when, classification of dressing up can be obtained.User can select required classification of dressing up, such as trend dress in mobile terminal
Play the part of, chivalrous person dresss up, occupation is dressed up, but not limited to this.Database can be previously stored with the ginseng of dressing up for belonging to different classifications of dressing up
Count, the vertex information for building 3D models is may include in parameter of dressing up, available for the clothes for showing different classification styles of dressing up
Decorations, hair style, dressing etc. are dressed up effect.
Step 704, corresponding with physical parameter second is chosen in classification of dressing up to dress up parameter.
Server determination is dressed up after classification, and what can be stored from database belongs in the parameter of dressing up of same classification of dressing up,
Corresponding with physical parameter second is chosen to dress up parameter, if for example, target object behaviour, sex that can be according to target object, body
Height, shape of face etc. second are dressed up parameter corresponding to choosing.Further, dress ornament corresponding with the physical parameter of target object can be chosen
Parameter, hair style parameter, dressing parameter etc..
Step 706, according to physical parameter and second dress up parameter structure target object 3D models.
The server parameter that can be dressed up according to the physical parameter of target object and the second of selection builds target object jointly
3D models, and the target object of 2D images is replaced with to the 3D models of structure, obtain 3D rendering.Server can return to 3D rendering
To mobile terminal, the 3D models dressed up with specific dress ornament, hair style or dressing etc. can be shown on mobile terminals.
In the present embodiment, 2D images can be converted to and includes the 3D rendering with the specific 3D models dressed up, make figure
As beholder can perceive more image informations, the visual display effect of image is improved.
In one embodiment, after step builds the 3D models of target object according to physical parameter, at above-mentioned image
Reason method is further comprising the steps of：
Step (a), target action is determined according to processing type, and obtain the action data matched with the target action.
After server receives the image processing requests that mobile terminal is sent, processing type can be obtained, when processing type is mesh
When marking object motion processing, target action can be obtained.User can select required target action in mobile terminal, make 2D images
The posture of target action is presented in target object, for example, the target object of 2D images is behaved, at user option action may include
Fly, jump etc., but not limited to this.The action data of substantial amounts of different actions can be previously stored with database, action data can
Including the vertex information for building 3D models, the 3D models of structure are made to show corresponding action.
Step (b), the 3D models of target object are built according to physical parameter and action data.
Server can be according to the physical parameter of target object and the action data of acquisition, the common 3D moulds for building target object
Type, and the target object of 2D images is replaced with to the 3D models of structure, obtain 3D rendering.Server can return to 3D rendering shifting
Dynamic terminal, can show the 3D models for showing specific action on mobile terminals.
Selected it is to be appreciated that above-mentioned several different disposal types are stackable, for example, user can be in mobile terminal
Simultaneous selection carries out virtual scene processing and target object action to 2D images and handled, also can simultaneous selection target object dress up place
Reason and target object action processing etc., make finally to convert the obtained a variety of different 3D effects of 3D rendering presentation.
In the present embodiment, 2D images can be converted to the 3D rendering for including the 3D models with specific action posture,
Enabling image-watching, person perceives more image informations, improves the visual display effect of image.
In one embodiment, there is provided a kind of image processing method, comprise the following steps：
Step (1), receives the image processing requests that mobile terminal is sent, and image processing requests include pending 2D images
And processing type.
Step (2), 2D images are divided into foreground area and the background area in addition to foreground area, and extract prospect respectively
Region and the characteristics of image of background area, foreground area include target object.
Step (3), similarity mode calculating is carried out to the characteristics of image of foreground area in database, identification 2D images
Target object, and obtain the physical parameter matched with target object.
Step (4), when it is that single goal object turns 3D processing to handle type, form parameter in physical parameter and big
Small parameter builds the 3D grid models of target object in proportion, and 3D grid models are rendered further according to parametric texture, structure
The 3D models of target object, and the target object of 2D images is replaced with into 3D models, obtain 3D rendering.
Step (5), when it is that panorama is handled to handle type, according to the form parameter of physical parameter and size parameter in proportion
The 3D grid models of target object are built, the 3D grid models are rendered further according to parametric texture, build target object
3D models；Similarity mode calculating is carried out to the characteristics of image of background area in database, identifies the picture field of 2D images
Scape, the multi-angle scene image matched with image scene is obtained from database, it is complete to synthesize 3D further according to multi-angle scene image
Scape scene image, and by 3D panoramic scenes image and the 3D Model Fusions of target object, obtain 3D rendering.
Step (6), when it is that virtual scene is handled to handle type, destination virtual scene is determined according to processing type, and obtain
The virtual scene data with destination virtual scene matching are taken, 3D virtual scene images are built according to virtual scene data；When virtual
Contextual data include with the first of destination virtual scene matching dress up parameter when, dressed up parameter structure according to physical parameter and first
Build the 3D models of target object, and by 3D virtual scenes image and the 3D Model Fusions of target object, obtain 3D rendering.
Step (7), when processing type is that target object is dressed up processing, is dressed up classification according to processing type determination, dressed up
Corresponding with physical parameter second is chosen in classification to dress up parameter, and target object is built according to the parameter of dressing up of physical parameter and second
3D models, and the target object of 2D images is replaced with into 3D models, obtains 3D rendering.
Step (8), mobile terminal is returned to by 3D rendering.
In the present embodiment, 2D images can be converted into by 3D rendering based on big data automatically, enabling image-watching, person perceives
More image informations, it is simple and efficient.And the target object of 2D images is identified by big data, obtain what is matched with target object
Physical parameter, more information on target object can be obtained, make that the 3D models of structure are truer, possess more details.In addition, can
Different 3D conversion process is carried out to 2D images, improves the visual display effect of image.
As shown in figure 8, in one embodiment, there is provided a kind of image processing apparatus 800, including receiving module 810, extraction
Module 820, identification module 830, structure module 840 and sending module 850.
Receiving module 810, for receiving the image processing requests of mobile terminal transmission, image processing requests include pending
2D images.
Extraction module 820, for extracting the characteristics of image of 2D images.
Identification module 830, for carrying out similarity mode calculating to characteristics of image in database, identify the mesh of 2D images
Object is marked, and obtains the physical parameter matched with target object.
Module 840 is built, for building the 3D models of target object according to physical parameter, and by the target object of 2D images
3D models are replaced with, obtain 3D rendering.
Sending module 850, for 3D rendering to be returned into mobile terminal.
In the present embodiment, similarity mode calculating can be carried out to the characteristics of image of the 2D images of extraction in database,
The target object of 2D images is identified, and the physical parameter matched according to target object builds the 3D models of target object, can be based on
2D images are converted into 3D rendering by big data automatically, and enabling image-watching, person perceives more image informations, simple and efficient.It is and logical
The target object of big data identification 2D images is crossed, the physical parameter matched with target object is obtained, more targets can be obtained
Object information, makes that the 3D models of structure are truer, possess more details.
In one embodiment, physical parameter includes form parameter, size parameter and parametric texture.
Build module 840, including grid model construction unit and rendering unit.
Grid model construction unit, for building the 3D grids of target object in proportion according to form parameter and size parameter
Model.
Rendering unit, for being rendered according to parametric texture to 3D grid models.
In the present embodiment, the 3D models of target object in 2D images can be generated based on big data, by the 2D images of plane
The 3D rendering of solid is converted into, enabling image-watching, person perceives more image informations, and simple and efficient.
In one embodiment, extraction module 820, it is additionally operable to 2D images being divided into foreground area and in addition to foreground area
Background area, and extract the characteristics of image of foreground area and background area respectively, foreground area includes target object.
In the present embodiment, 2D images are divided into foreground area and background area, can be only special to the image of foreground area
Sign is analyzed, and identifies the target object of 2D images, recognition result can be made more accurate, reduces noise.
In one embodiment, image processing requests include processing type, and processing type includes panorama processing.
Identification module 830, it is additionally operable to carry out similarity mode calculating to the characteristics of image of background area in database, knows
The image scene of other 2D images.
Above-mentioned image processing apparatus 800, except including receiving module 810, extraction module 820, identification module 830, structure
Module 840 and sending module 850, in addition to scene image acquisition module and synthesis module.
Scene image acquisition module, for obtaining the multi-angle scene image matched with image scene from database.
Synthesis module, for synthesizing 3D panoramic scene images according to multi-angle scene image, and by 3D panoramic scene images
With the 3D Model Fusions of target object, 3D rendering is obtained.
In the present embodiment, 2D images can be converted to the 3D rendering for including 3D panoramic scenes, the person that enables image-watching
More image informations are perceived, improve the visual display effect of image.
In one embodiment, handling type includes virtual scene processing.
Above-mentioned image processing apparatus 800, in addition to virtual scene data acquisition module.
Virtual scene data acquisition module, destination virtual scene is determined according to processing type, and obtained and destination virtual field
The virtual scene data of scape matching.
Module 840 is built, is additionally operable to build 3D virtual scene images according to virtual scene data, and by 3D virtual scene figures
As the 3D Model Fusions with target object, 3D rendering is obtained.
In one embodiment, module 840 is built, is additionally operable to when virtual scene packet contains and destination virtual scene
First matched somebody with somebody dress up parameter when, according to physical parameter and first dress up parameter structure target object 3D models.
In the present embodiment, 2D images can be converted to the 3D rendering for including 3D virtual scenes, the person that enables image-watching
More image informations are perceived, improve the visual display effect of image.
In one embodiment, type is handled including target object to dress up processing.
Above-mentioned image processing apparatus 800, in addition to category determination module.
Category determination module, for determining classification of dressing up according to processing type, and choose in classification of dressing up and join with physics
Second dresss up parameter corresponding to number.
Build module 840, be additionally operable to according to the physical parameter and second dress up parameter structure target object 3D models.
In the present embodiment, 2D images can be converted to and includes the 3D rendering with the specific 3D models dressed up, make figure
As beholder can perceive more image informations, the visual display effect of image is improved.
In one embodiment, there is provided a kind of server, including memory and processor, store computer in memory
Program, when computer program instructions are executed by processor so that processor realizes above-mentioned image processing method.
In one embodiment, there is provided a kind of computer-readable recording medium, be stored thereon with computer program, computer
Above-mentioned image processing method is realized when program is executed by processor.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can be read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
Any reference to memory, storage, database or other media may include non-volatile as used herein
And/or volatile memory.Suitable nonvolatile memory may include read-only storage (ROM), programming ROM (PROM),
Electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include arbitrary access
Memory (RAM), it is used as external cache.By way of illustration and not limitation, RAM is available in many forms, such as
It is static RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDR SDRAM), enhanced
SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM).
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the application, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, on the premise of the application design is not departed from, various modifications and improvements can be made, these belong to the protection of the application
Scope.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
- A kind of 1. image processing method, it is characterised in that including：The image processing requests that mobile terminal is sent are received, described image processing request includes pending 2D images；Extract the characteristics of image of the 2D images；Similarity mode calculating is carried out to described image feature in database, identifies the target object of the 2D images, and obtain Take the physical parameter matched with the target object；The 3D models of the target object are built according to the physical parameter, and the target object of the 2D images is replaced with into institute 3D models are stated, obtain 3D rendering；The 3D rendering is returned into the mobile terminal.
- 2. according to the method for claim 1, it is characterised in that the physical parameter include form parameter, size parameter and Parametric texture；The 3D models that the target object is built according to the physical parameter, including：Build the 3D grid models of the target object in proportion according to the form parameter and size parameter；The 3D grid models are rendered according to the parametric texture.
- 3. method according to claim 1 or 2, it is characterised in that the characteristics of image of the extraction 2D images, bag Include：The 2D images are divided into foreground area and the background area in addition to the foreground area, and extract the prospect respectively Region and the characteristics of image of background area, the foreground area include target object.
- 4. according to the method for claim 3, it is characterised in that described image processing request includes handling type, the place Managing type includes panorama processing；After the 3D models that the target object is built according to the physical parameter, methods described also includes：Similarity mode calculating is carried out to the characteristics of image of the background area in the database, identifies the 2D images Image scene；The multi-angle scene image with described image scene matching is obtained from the database；3D panoramic scene images are synthesized according to the multi-angle scene image, and by the 3D panoramic scenes image and the target The 3D Model Fusions of object, obtain 3D rendering.
- 5. according to the method for claim 4, it is characterised in that the processing type includes virtual scene processing；After the 3D models that the target object is built according to the physical parameter, methods described also includes：Destination virtual scene is determined according to the processing type, and obtains the virtual scene number with the destination virtual scene matching According to；3D virtual scene images are built according to the virtual scene data；By the 3D virtual scenes image and the 3D Model Fusions of the target object, 3D rendering is obtained.
- 6. according to the method for claim 5, it is characterised in that described that the target object is built according to the physical parameter 3D models, including：When the virtual scene packet contain with the first of the destination virtual scene matching dress up parameter when, according to the thing Reason parameter and the described first parameter of dressing up build the 3D models of the target object.
- 7. according to the method for claim 4, it is characterised in that the processing type is dressed up processing including target object；After the physical parameter for obtaining and being matched with the target object, methods described also includes：Classification of dressing up is determined according to the processing type；Corresponding with the physical parameter second is chosen in the classification of dressing up to dress up parameter；The 3D models of the target object are built according to the parameter of dressing up of the physical parameter and second.
- A kind of 8. image processing apparatus, it is characterised in that including：Receiving module, for receiving the image processing requests of mobile terminal transmission, described image processing request includes pending 2D images；Extraction module, for extracting the characteristics of image of the 2D images；Identification module, for carrying out similarity mode calculating to described image feature in database, identify the 2D images Target object, and obtain the physical parameter matched with the target object；Module is built, for building the 3D models of the target object according to the physical parameter, and by the mesh of the 2D images Mark object replaces with the 3D models, obtains 3D rendering；Sending module, for the 3D rendering to be returned into the mobile terminal.
- 9. a kind of server, including memory and processor, computer program, the computer journey are stored in the memory When sequence instruction is by the computing device so that the processor realizes the method as described in claim 1 to 7 is any.
- 10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the computer program The method as described in claim 1 to 7 is any is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710737532.7A CN107393000B (en) | 2017-08-24 | 2017-08-24 | Image processing method, image processing device, server and computer-readable storage medium |
| CN202010603502.9A CN111768496B (en) | 2017-08-24 | 2017-08-24 | Image processing method, device, server and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710737532.7A CN107393000B (en) | 2017-08-24 | 2017-08-24 | Image processing method, image processing device, server and computer-readable storage medium |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010603502.9A Division CN111768496B (en) | 2017-08-24 | 2017-08-24 | Image processing method, device, server and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107393000A true CN107393000A (en) | 2017-11-24 |
| CN107393000B CN107393000B (en) | 2020-07-28 |
Family
ID=60345947
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010603502.9A Active CN111768496B (en) | 2017-08-24 | 2017-08-24 | Image processing method, device, server and computer readable storage medium |
| CN201710737532.7A Active CN107393000B (en) | 2017-08-24 | 2017-08-24 | Image processing method, image processing device, server and computer-readable storage medium |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010603502.9A Active CN111768496B (en) | 2017-08-24 | 2017-08-24 | Image processing method, device, server and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111768496B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898643A (en) * | 2018-06-15 | 2018-11-27 | 广东数相智能科技有限公司 | Image generating method, device and computer readable storage medium |
| CN109639969A (en) * | 2018-12-12 | 2019-04-16 | 维沃移动通信（杭州）有限公司 | A kind of image processing method, terminal and server |
| CN109840934A (en) * | 2017-11-29 | 2019-06-04 | 深圳市掌网科技股份有限公司 | A kind of the threedimensional model generation method and system of workpiece |
| WO2019128543A1 (en) * | 2017-12-30 | 2019-07-04 | Midea Group Co., Ltd. | Food preparation method and system based on ingredient recognition |
| CN110363224A (en) * | 2019-06-19 | 2019-10-22 | 创新奇智(北京)科技有限公司 | A kind of object classification method based on image, system and electronic equipment |
| WO2019214505A1 (en) * | 2018-05-06 | 2019-11-14 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Communication methods and systems, electronic devices, servers, and readable storage media |
| CN110914871A (en) * | 2018-07-27 | 2020-03-24 | 深圳市大疆创新科技有限公司 | Method and device for acquiring three-dimensional scene |
| CN111192368A (en) * | 2020-01-15 | 2020-05-22 | 石家庄中扬网络科技股份有限公司 | Three-dimensional model display method, terminal device and storage medium |
| CN111199511A (en) * | 2018-11-19 | 2020-05-26 | 北京京东尚科信息技术有限公司 | Graph generation method and device and computer readable storage medium |
| CN111447504A (en) * | 2020-03-27 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Three-dimensional video processing method and device, readable storage medium and electronic equipment |
| CN111598976A (en) * | 2019-02-01 | 2020-08-28 | 华为技术有限公司 | Scene recognition method and device, terminal and storage medium |
| CN111627118A (en) * | 2020-06-02 | 2020-09-04 | 上海商汤智能科技有限公司 | Scene portrait showing method and device, electronic equipment and storage medium |
| CN111862305A (en) * | 2020-06-30 | 2020-10-30 | 北京百度网讯科技有限公司 | Method, apparatus, and computer storage medium for processing image |
| CN112612980A (en) * | 2020-12-22 | 2021-04-06 | 北京百度网讯科技有限公司 | Picture service method, device, equipment, storage medium and computer program product |
| CN114660994A (en) * | 2022-05-25 | 2022-06-24 | 中科航迈数控软件(深圳)有限公司 | Decision optimization method, system and related equipment for machining process of numerical control machine tool |
| US20220245375A1 (en) * | 2021-01-30 | 2022-08-04 | David Young | Volumetric Security |
| CN114926351A (en) * | 2022-04-12 | 2022-08-19 | 荣耀终端有限公司 | Image processing method, electronic device, and computer storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348944B (en) * | 2020-10-29 | 2022-06-28 | 久瓴(江苏)数字智能科技有限公司 | Three-dimensional model data updating method, device, computer equipment and storage medium |
| CN112577488B (en) * | 2020-11-24 | 2022-09-02 | 腾讯科技（深圳）有限公司 | Navigation route determining method, navigation route determining device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006243458A (en) * | 2005-03-04 | 2006-09-14 | C's Lab Ltd | Three dimensional map display device and three dimensional map display program |
| US20070078848A1 (en) * | 2005-10-04 | 2007-04-05 | Microsoft Corporation | Indexing and caching strategy for local queries |
| US20120176477A1 (en) * | 2004-07-30 | 2012-07-12 | Dor Givon | Methods, Systems, Devices and Associated Processing Logic for Generating Stereoscopic Images and Video |
| CN103729885A (en) * | 2014-01-21 | 2014-04-16 | 北京邮电大学 | Hand-drawn scene three-dimensional modeling method combining multi-perspective projection with three-dimensional registration |
| CN104658034A (en) * | 2013-11-18 | 2015-05-27 | 清华大学 | Fusion rendering method for CT (Computed Tomography) image data |
| CN105551084A (en) * | 2016-01-28 | 2016-05-04 | 北京航空航天大学 | Outdoor three-dimensional scene combined construction method based on image content parsing |
| CN105913485A (en) * | 2016-04-06 | 2016-08-31 | 北京小小牛创意科技有限公司 | Three-dimensional virtual scene generation method and device |
| CN107038751A (en) * | 2015-12-07 | 2017-08-11 | 达索系统公司 | The identification of 3D modeling object is carried out from 2D images |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143212A (en) * | 2014-07-02 | 2014-11-12 | 惠州Tcl移动通信有限公司 | Reality augmenting method and system based on wearable device |
| CN104504671B (en) * | 2014-12-12 | 2017-04-19 | 浙江大学 | Method for generating virtual-real fusion image for stereo display |
| CN104656893B (en) * | 2015-02-06 | 2017-10-13 | 西北工业大学 | The long-distance interactive control system and method in a kind of information physical space |
| CN105825544B (en) * | 2015-11-25 | 2019-08-20 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| US10257505B2 (en) * | 2016-02-08 | 2019-04-09 | Microsoft Technology Licensing, Llc | Optimized object scanning using sensor fusion |
-
2017
- 2017-08-24 CN CN202010603502.9A patent/CN111768496B/en active Active
- 2017-08-24 CN CN201710737532.7A patent/CN107393000B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120176477A1 (en) * | 2004-07-30 | 2012-07-12 | Dor Givon | Methods, Systems, Devices and Associated Processing Logic for Generating Stereoscopic Images and Video |
| JP2006243458A (en) * | 2005-03-04 | 2006-09-14 | C's Lab Ltd | Three dimensional map display device and three dimensional map display program |
| US20070078848A1 (en) * | 2005-10-04 | 2007-04-05 | Microsoft Corporation | Indexing and caching strategy for local queries |
| US7634465B2 (en) * | 2005-10-04 | 2009-12-15 | Microsoft Corporation | Indexing and caching strategy for local queries |
| CN104658034A (en) * | 2013-11-18 | 2015-05-27 | 清华大学 | Fusion rendering method for CT (Computed Tomography) image data |
| CN103729885A (en) * | 2014-01-21 | 2014-04-16 | 北京邮电大学 | Hand-drawn scene three-dimensional modeling method combining multi-perspective projection with three-dimensional registration |
| CN107038751A (en) * | 2015-12-07 | 2017-08-11 | 达索系统公司 | The identification of 3D modeling object is carried out from 2D images |
| CN105551084A (en) * | 2016-01-28 | 2016-05-04 | 北京航空航天大学 | Outdoor three-dimensional scene combined construction method based on image content parsing |
| CN105913485A (en) * | 2016-04-06 | 2016-08-31 | 北京小小牛创意科技有限公司 | Three-dimensional virtual scene generation method and device |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840934A (en) * | 2017-11-29 | 2019-06-04 | 深圳市掌网科技股份有限公司 | A kind of the threedimensional model generation method and system of workpiece |
| CN111684368B (en) * | 2017-12-30 | 2021-11-19 | 美的集团股份有限公司 | Food preparation method and system based on ingredient identification |
| WO2019128543A1 (en) * | 2017-12-30 | 2019-07-04 | Midea Group Co., Ltd. | Food preparation method and system based on ingredient recognition |
| US11229311B2 (en) | 2017-12-30 | 2022-01-25 | Midea Group Co., Ltd. | Food preparation system |
| KR20200092380A (en) * | 2017-12-30 | 2020-08-03 | 미디어 그룹 코 엘티디 | Food preparation method and system based on material recognition |
| KR102329592B1 (en) | 2017-12-30 | 2021-11-19 | 미디어 그룹 코 엘티디 | Food preparation methods and systems based on ingredient recognition |
| CN111684368A (en) * | 2017-12-30 | 2020-09-18 | 美的集团股份有限公司 | Food preparation method and system based on ingredient identification |
| US11595635B2 (en) | 2018-05-06 | 2023-02-28 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Communication methods and systems, electronic devices, servers, and readable storage media |
| WO2019214505A1 (en) * | 2018-05-06 | 2019-11-14 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Communication methods and systems, electronic devices, servers, and readable storage media |
| US10785468B2 (en) | 2018-05-06 | 2020-09-22 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Communication methods and systems, electronic devices, servers, and readable storage media |
| CN108898643B (en) * | 2018-06-15 | 2022-03-11 | 广东数相智能科技有限公司 | Image generation method, device and computer readable storage medium |
| CN108898643A (en) * | 2018-06-15 | 2018-11-27 | 广东数相智能科技有限公司 | Image generating method, device and computer readable storage medium |
| CN110914871A (en) * | 2018-07-27 | 2020-03-24 | 深圳市大疆创新科技有限公司 | Method and device for acquiring three-dimensional scene |
| CN111199511A (en) * | 2018-11-19 | 2020-05-26 | 北京京东尚科信息技术有限公司 | Graph generation method and device and computer readable storage medium |
| CN109639969B (en) * | 2018-12-12 | 2021-01-26 | 维沃移动通信（杭州）有限公司 | Image processing method, terminal and server |
| CN109639969A (en) * | 2018-12-12 | 2019-04-16 | 维沃移动通信（杭州）有限公司 | A kind of image processing method, terminal and server |
| US11918900B2 (en) | 2019-02-01 | 2024-03-05 | Huawei Technologies Co., Ltd. | Scene recognition method and apparatus, terminal, and storage medium |
| CN111598976B (en) * | 2019-02-01 | 2023-08-22 | 华为技术有限公司 | Scene recognition method and device, terminal and storage medium |
| CN111598976A (en) * | 2019-02-01 | 2020-08-28 | 华为技术有限公司 | Scene recognition method and device, terminal and storage medium |
| CN110363224A (en) * | 2019-06-19 | 2019-10-22 | 创新奇智(北京)科技有限公司 | A kind of object classification method based on image, system and electronic equipment |
| CN110363224B (en) * | 2019-06-19 | 2021-07-06 | 创新奇智(北京)科技有限公司 | Object classification method and system based on image and electronic equipment |
| CN111192368B (en) * | 2020-01-15 | 2022-06-24 | 石家庄中扬网络科技股份有限公司 | Three-dimensional model display method, terminal device and storage medium |
| CN111192368A (en) * | 2020-01-15 | 2020-05-22 | 石家庄中扬网络科技股份有限公司 | Three-dimensional model display method, terminal device and storage medium |
| WO2021190229A1 (en) * | 2020-03-27 | 2021-09-30 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing three-dimensional video, readable storage medium, and electronic device |
| CN111447504A (en) * | 2020-03-27 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Three-dimensional video processing method and device, readable storage medium and electronic equipment |
| US11785195B2 (en) | 2020-03-27 | 2023-10-10 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for processing three-dimensional video, readable storage medium and electronic device |
| CN111627118A (en) * | 2020-06-02 | 2020-09-04 | 上海商汤智能科技有限公司 | Scene portrait showing method and device, electronic equipment and storage medium |
| CN111862305A (en) * | 2020-06-30 | 2020-10-30 | 北京百度网讯科技有限公司 | Method, apparatus, and computer storage medium for processing image |
| CN112612980A (en) * | 2020-12-22 | 2021-04-06 | 北京百度网讯科技有限公司 | Picture service method, device, equipment, storage medium and computer program product |
| CN112612980B (en) * | 2020-12-22 | 2024-03-01 | 北京百度网讯科技有限公司 | Picture service method, apparatus, device, storage medium and computer program product |
| US20220245375A1 (en) * | 2021-01-30 | 2022-08-04 | David Young | Volumetric Security |
| CN114926351B (en) * | 2022-04-12 | 2023-06-23 | 荣耀终端有限公司 | Image processing method, electronic device, and computer storage medium |
| CN114926351A (en) * | 2022-04-12 | 2022-08-19 | 荣耀终端有限公司 | Image processing method, electronic device, and computer storage medium |
| CN114660994B (en) * | 2022-05-25 | 2022-08-23 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool machining process decision optimization method, system and related equipment |
| CN114660994A (en) * | 2022-05-25 | 2022-06-24 | 中科航迈数控软件(深圳)有限公司 | Decision optimization method, system and related equipment for machining process of numerical control machine tool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107393000B (en) | 2020-07-28 |
| CN111768496A (en) | 2020-10-13 |
| CN111768496B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107393000A (en) | Image processing method, device, server and computer-readable recording medium | |
| CN110515452B (en) | Image processing method, image processing device, storage medium and computer equipment | |
| JP6956252B2 (en) | Facial expression synthesis methods, devices, electronic devices and computer programs | |
| US10593104B2 (en) | Systems and methods for generating time discrete 3D scenes | |
| CN110738595B (en) | Picture processing method, device and equipment and computer storage medium | |
| JP2006053694A (en) | Space simulator, space simulation method, space simulation program and recording medium | |
| CN109474780A (en) | A kind of method and apparatus for image procossing | |
| US11393228B2 (en) | Methods, systems, articles of manufacture and apparatus to generate digital scenes | |
| CN108111911B (en) | Video data real-time processing method and device based on self-adaptive tracking frame segmentation | |
| CN113657357B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US11900552B2 (en) | System and method for generating virtual pseudo 3D outputs from images | |
| CN113760161A (en) | Data generation method, data generation device, image processing method, image processing device, equipment and storage medium | |
| CN110049180A (en) | Shoot posture method for pushing and device, intelligent terminal | |
| GB2597517A (en) | Method and system for generating a target image from plural multi-plane images | |
| CN114693853A (en) | Object rendering method and device, electronic equipment and storage medium | |
| CN110266926A (en) | Image processing method, device, mobile terminal and storage medium | |
| Wang et al. | Neural opacity point cloud | |
| CN109445569A (en) | Information processing method, device, equipment and readable storage medium storing program for executing based on AR | |
| CN111402118A (en) | Image replacement method and device, computer equipment and storage medium | |
| CN110177216A (en) | Image processing method, device, mobile terminal and storage medium | |
| Liu et al. | Fog effect for photography using stereo vision | |
| WO2022217470A1 (en) | Hair rendering system based on deep neural network | |
| Patterson et al. | Landmark-based re-topology of stereo-pair acquired face meshes | |
| JP6341540B2 (en) | Information terminal device, method and program | |
| KR101399633B1 (en) | Method and apparatus of composing videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |