CN108124148A - A kind of method and device of the multiple view images of single view video conversion - Google Patents
A kind of method and device of the multiple view images of single view video conversion Download PDFInfo
- Publication number
- CN108124148A CN108124148A CN201711158453.7A CN201711158453A CN108124148A CN 108124148 A CN108124148 A CN 108124148A CN 201711158453 A CN201711158453 A CN 201711158453A CN 108124148 A CN108124148 A CN 108124148A
- Authority
- CN
- China
- Prior art keywords
- view image
- offset
- pixel
- single view
- default parallax
- 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.)
- Pending
Links
Abstract
The embodiment of the invention discloses a kind of method and devices of the single multiple view images of view video conversion.The described method includes：Obtain pending single view image；According to default parallax template, the corresponding at least one offset of pixel in the single view image is determined, and migration processing at least once is carried out to pixel according at least one offset, obtain at least one view image.By using above-mentioned technical proposal, solves the limitation that single view image is converted to multiple view images with parallax in real time in the limited mobile equipment of processing capacity, good image resource is provided for the follow-up real-time display 3-D view of the small mobile terminals such as mobile phone or tablet computer, improves user experience.
Description
Technical field
The present embodiments relate to technical field of image processing more particularly to a kind of single multiple views of view video conversion
The method and device of image.
Background technology
Parallax carries out play important role in three-dimensional perception in the mankind.Since Euclid's period, people just recognize
Know, why the mankind can carry out three-dimensional perception, and it is variant to be primarily due to the image that right and left eyes are seen, to this species diversity
Quantified to be known as parallax.Therefore, the image with parallax is particularly significant for stereo display effect is presented.
It is abundant in content since the video content of 2D (two dimension) image is saved bit by bit for many years, therefore, by the way that 2D images are converted to
During subsequent image is applied, 3D (three is synthesized especially with transformed multiple images for multiple images with parallax
Dimension) image stereo display effect is presented when, considerable economic value can be brought.
However, in the prior art, it is necessary to extract image when single 2D images are converted to the multiple images with parallax
Depth information, then again by depth information be converted into parallax mapping.Since above-mentioned calculating process is complex, calculation amount compared with
Greatly, it is higher to the calculating processing Capability Requirement of display device, therefore, above-mentioned image conversion regime can not compatible processing ability have
The processor of limit, such as practicability and real-time are poor for the small mobile terminals such as mobile phone or tablet computer.
The content of the invention
The embodiment of the present invention provides a kind of method and device of the single multiple view images of view video conversion, realizes
By single view video conversion it is multiple view images in the limited small mobile terminals of processing capacity, and improves the reality of conversion
Shi Xing.
To achieve the above object, the embodiment of the present invention adopts the following technical scheme that：
In a first aspect, an embodiment of the present invention provides a kind of method of the single multiple view images of view video conversion, institutes
The method of stating includes：
Obtain pending single view image；
According to default parallax template, the corresponding at least one offset of pixel in the single view image is determined, and
Migration processing at least once is carried out to pixel according at least one offset, obtains at least one view image.
Further, the default parallax template is default parallax function or at least one default parallax form, for table
Show in the single view image that the coordinate value of each pixel and each pixel need to be carried out between the offset of migration processing
Relation.
Further, the default parallax template is default parallax function；
Correspondingly, according to default parallax template, determine that pixel is corresponding at least one inclined in the single view image
Shifting amount, including：
According to following default parallax function, the corresponding at least one offset of pixel in the single view image is calculated
Amount：
Offset_ij=F (x, y, σ),
Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in the single view image, and y single regards to be described
The ordinate value for the pixel that the i-th row jth arranges, σ generate the variation coefficient of at least one offset in order to control in figure image；
Offset_ij is the corresponding offset of pixel of the i-th row jth row；
Correspondingly, carrying out migration processing at least once to pixel according at least one offset, at least one is obtained
A view image, including：
The abscissa value of pixel in the single view image is carried out at least according at least one offset
Migration processing, ordinate value remain unchanged, and obtain at least one view image.
Further, the default parallax template is at least one default parallax form；
Correspondingly, according to default parallax template, determine that pixel is corresponding at least one inclined in the single view image
Shifting amount, and migration processing at least once is carried out to pixel according at least one offset, obtain at least one view shadow
Picture, including：
According to the coordinate value of pixel in single view image, at least one default parallax form is inquired about, is determined each
A corresponding at least one offset of pixel, and each pixel is carried out at least according at least one offset
Migration processing obtains at least one view image.
Further, after obtaining at least one view image, the method further includes：
The single view image and at least one view image are interleaved processing, form 3-D view.
Further, when generating a view image, then using a view image of generation as target view image；
Correspondingly, the single view image and at least one view image are interleaved processing, formed three-dimensional
Image, including：
Row pixel transpostion interval in the single view image and target view image is arranged, forms stereopsis,
For bore hole 3D display.
Further, the default parallax template is corresponding with the scene of the single view image, and the scene includes
Personage's scene, landscape scene or moving scene.
Second aspect, an embodiment of the present invention provides a kind of device of the single multiple view images of view video conversion, institutes
Stating device includes：
Single view image acquiring module, for obtaining pending single view image；
Multiple view image determining modules, for according to default parallax template, determining pixel in the single view image
The corresponding at least one offset of point, and migration processing at least once is carried out to pixel according at least one offset,
Obtain at least one view image.
Further, the default parallax template is default parallax function or at least one default parallax form, for table
Show in the single view image that the coordinate value of each pixel and each pixel need to be carried out between the offset of migration processing
Relation.
Further, the default parallax template is default parallax function；Correspondingly, the multiple view image determines mould
Block includes offset computation unit and multiple view image determination units：Wherein,
The offset computation unit, for according to default parallax function as follows, calculating picture in the single view image
The corresponding at least one offset of vegetarian refreshments：
Offset_ij=F (x, y, σ),
Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in the single view image, and y single regards to be described
The ordinate value for the pixel that the i-th row jth arranges, σ generate the variation coefficient of at least one offset in order to control in figure image；
Offset_ij is the corresponding offset of pixel of the i-th row jth row；
The multiple view image determination unit, for the abscissa value of the pixel in the single view image to be pressed
Migration processing, ordinate value at least once are carried out according at least one offset to remain unchanged, and obtain at least one view shadow
Picture.
Further, the default parallax template is at least one default parallax form；
Correspondingly, the multiple view image determining module is specifically used for：According to the seat of pixel in single view image
Scale value inquires about at least one default parallax form, determines the corresponding at least one offset of each pixel, and press
Migration processing at least once is carried out to each pixel according at least one offset, obtains at least one view image.
Further, described device further includes：3-D view generation module, for obtain at least one view image it
Afterwards, the single view image and at least one view image are interleaved processing, form 3-D view.
Further, when generating a view image, then using a view image of generation as target view image；
Correspondingly, the 3-D view generation module is specifically used for：By the single view image and target view image
Middle row pixel transpostion interval arrangement, forms stereopsis, for bore hole 3D display.
Further, the default parallax template is corresponding with the scene of the single view image, and the scene includes
Personage's scene, landscape scene or moving scene.
In the technical solution of the embodiment of the present invention, by obtaining pending single view image, and according to default parallax
Template determined in single view image after at least one offset of pixel, can be according at least one offset to pixel
Migration processing at least once is carried out, obtains at least one view image.Compared with the realization method that the prior art provides, the present invention
The technical solution that embodiment provides by single view video conversion for during multiple view images with parallax, without
Obtain the depth information of single-view, there are no depth information need to be converted into parallax mapping, calculating process and calculation amount compared with
The technical solution that the prior art provides significantly is reduced, and is solved and is regarded in the limited mobile equipment of processing capacity by single
Figure image is converted to the limitation of multiple view images with parallax in real time, is the small mobile terminals such as mobile phone or tablet computer
Follow-up real-time display 3-D view provides good image resource, improves user experience.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without creative efforts, can also implement according to the present invention
The content of example and these attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow of the method for single multiple view images of view video conversion that the embodiment of the present invention one provides
Schematic diagram；
Fig. 2 is a kind of pixel-shift schematic diagram that the embodiment of the present invention one provides；
Fig. 3 is a kind of flow of the method for the single multiple view images of view video conversion provided by Embodiment 2 of the present invention
Schematic diagram；
Fig. 4 is a kind of structure of the device for single multiple view images of view video conversion that the embodiment of the present invention three provides
Block diagram.
Specific embodiment
For make present invention solves the technical problem that, the technical solution that uses and the technique effect that reaches it is clearer, below
The technical solution of the embodiment of the present invention will be described in further detail with reference to attached drawing, it is clear that described embodiment is only
It is part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
All other embodiments obtained under the premise of creative work are not made, belong to the scope of protection of the invention.
Embodiment one
Fig. 1 is a kind of flow of the method for single multiple view images of view video conversion that the embodiment of the present invention one provides
Schematic diagram.The method of the present embodiment can be performed by the device of the multiple view images of single view video conversion, wherein, the dress
Putting can be generally integrated in the mobile terminals such as tablet computer or mobile phone, which can cloth by software and/or hardware realization
Equipped with Grating Film, the display effect of bore hole 3D is used to implement.As shown in Figure 1, this method may include steps of：
S110：Obtain pending single view image.
Wherein, pending single view image can be real using the camera of the mobile terminals such as tablet computer or mobile phone
When the 2D images that shoot, or playing video or picture using the video in above-mentioned mobile terminal or picture players
When, each frame image data that GPU (Graphics Processing Unit, image processor) is obtained in real time.Illustratively,
The data basis that the single view image obtained can be shown as follow-up 3D rendering.
It, can be by the view Image preservation into corresponding with GPU processing formats after above-mentioned single view image is got
Texture format, to provide facility for GPU processing.
S120：According to default parallax template, the corresponding at least one offset of pixel in single view image is determined, and
Migration processing at least once is carried out to pixel according at least one offset, obtains at least one view image.
Wherein, it is default parallax function or default parallax form to preset parallax template, for representing in single view image
The coordinate value of each pixel and each pixel need to carry out the relation between the offset of migration processing.In default parallax template
The laying directional correlation of the Grating Film of the size and realization bore hole 3D display of the setting of offset and the display screen of mobile terminal.
Illustratively, if default parallax template is default parallax function, according to default parallax template, single regard is determined
The process of the corresponding at least one offset of pixel in figure image, is specifically as follows：
According to following default parallax function, the corresponding at least one offset of pixel in single view image is calculated：
Offset_ij=F (x, y, σ),
Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in single view image, and y is in single view image
The ordinate value of the pixel of i-th row jth row, σ generate the variation coefficient of at least one offset in order to control；Offset_ij is
The corresponding offset of pixel of i-th row jth row.
Illustratively, by indicating the variation coefficient σ in parallax function, it can control and single-view image is carried out at least once
Migration processing obtains at least one offset.Specifically, to only be carried out to pending single view image at once offset
The value of the parameter σ indicated in parallax function can be then set to a definite value by reason.
By using above-mentioned default parallax function, each pixel or sub-pixel in single view image can be calculated
Corresponding at least one offset, until completing the calculating to the corresponding multiple offsets of all pixels point.Wherein, for same
Secondary migration processing, the offset of different pixels point can be the same or different.
Correspondingly, carrying out migration processing at least once to pixel according at least one offset, at least one regard is obtained
The process of figure image, is specifically as follows：By the abscissa value of the pixel in single view image according at least one offset
Migration processing is carried out, ordinate value remains unchanged, and obtains at least one view image.Illustratively, specifically can be used following inclined
Move formula：
F (x ', y ')=f (x+offset_ij, y)；
Wherein, (x ', y ') is pixel coordinate of the pixel after migration processing in single view image, and x ' is process
Abscissa value after migration processing, y ' are the ordinate value after offset, and x is the i-th row jth row for not carrying out migration processing
The abscissa value of pixel, y are the ordinate value of the pixel for the i-th row jth row for not carrying out migration processing, and offset_ij is
The offset of the abscissa of the pixel of i-th row jth row.
By above-mentioned offset equation, the abscissa value of pixel changes, and then forms new image.In mobile terminal
When being handled in real time, due to reducing single-view conversion multi views by the way of carrying out offset calculating using default parallax function
Calculation amount so that image conversion real-time effectively promoted.
Specifically, Fig. 2 is a kind of pixel-shift schematic diagram that the embodiment of the present invention one provides.As shown in Fig. 2, for each
Secondary migration processing, in the case where the ordinate y values of pixel are constant, abscissa x values can be presented gradient as shown in Figure 2 and become
Change.
It illustratively, can be by way of tabling look-up, really when default parallax template is at least one default parallax form
The corresponding at least one offset of each pixel in order view image, realization method is simple, and calculation amount is smaller, can be with
In the mobile terminal limited applied to processing capacity.By according at least one offset inquired in single view image
Each pixel carry out migration processing at least once, can obtain at least one view image, and the real-time of image conversion obtains
To raising.
It should be noted that default parallax template can be corresponding with the scene of single-view image, wherein, single-view image
Scene can be people's object field scape, landscape scene or moving scene.Therefore, when user want to present on the display screen of mobile terminal it is naked
During eye 3D effect, can corresponding default parallax mould be selected according to the scene corresponding to the scene of image to be captured or video to be played
Plate.The advantages of this arrangement are as follows：The 3-D view finally shown in display screen is bonded the most with the scene of actual photographed, into
And preferable 3D display effect can be showed, promote the viewing experience of user.
In the technical solution of the embodiment of the present invention, by obtaining pending single view image, and according to default parallax
Template determined in single view image after at least one offset of pixel, can be according at least one offset to pixel
Migration processing at least once is carried out, obtains at least one view image.Compared with the realization method that the prior art provides, the present invention
The technical solution that embodiment provides by single view video conversion for during multiple view images with parallax, without
Obtain the depth information of single-view, there are no depth information need to be converted into parallax mapping, calculating process and calculation amount compared with
The technical solution that the prior art provides significantly is reduced, and is solved and is regarded in the limited mobile equipment of processing capacity by single
Figure image is converted to the limitation of multiple view images with parallax in real time, is the small mobile terminals such as mobile phone or tablet computer
Follow-up real-time display 3-D view provides good image resource, improves user experience.
Embodiment two
Fig. 3 is a kind of flow of the method for the single multiple view images of view video conversion provided by Embodiment 2 of the present invention
Schematic diagram.The present embodiment is optimized on the basis of above-described embodiment, and with reference to Fig. 3, the embodiment of the present invention two specifically includes
Following steps：
S210：Obtain pending single view image.
S220：According to default parallax template, the corresponding at least one offset of pixel in single view image is determined, and
Migration processing at least once is carried out to pixel according at least one offset, obtains at least one view image.
Illustratively, to obtain two view images with parallax, can be calculated by the value of parameter σ in adjustment function
Two different offsets in single view image or can also in default parallax form different default of selection two
Parallax form obtains two different offsets by enquiry form.
Specifically, according to the first default parallax form, can determine the first offset of the pixel in single view image,
And the first migration processing is carried out to pixel according to the first offset, obtain left view.According to the second default parallax form (with the
One default parallax form is different), determine the second offset of the pixel in single view image, and according to the second offset pair
Pixel carries out the second migration processing, obtains right view.
Wherein, since the first default parallax form is different from the second default parallax form, it is default to be respectively adopted first
The offset of pixel is also different in the single view image that parallax form is calculated from the second default parallax form.By right
After pixel in single view image carries out migration processing according to different offsets, between obtained left view and right view
There are certain parallaxes.Therefore, the calculating for being arranged to pixel offset of different parallax forms provides data basis, and then
It can obtain multiple view images with parallax.Specifically, the present embodiment is during definite left view and right view, without
The depth information of image is obtained from original single view image, compared with the technical solution of the prior art, simplifies computing
Journey reduces calculation amount, is applicable to the weaker mobile equipment of processing capacity.
It should be noted that obtain left view and right view carrying out migration processing to the pixel in single view image
Process be not present execution sequence limitation, can be carried out at the same time successively to carry out.
S230：Single view image and at least one view image are interleaved processing, form 3-D view.
Illustratively, after multiple view images are obtained based on single view image, the multiple view shadows that can will obtain
As the data basis as 3D rendering synthesis, for synthesizing 3D rendering in real time.
Further, after 3D rendering is synthesized, real-time display can be carried out on the display screen of mobile terminal, and can be formed naked
The display effect of eye 3D.
Preferably, if carry out bore hole 3D display using the obtained left views of step S220 and right view, arrange and scheme in software
During, it can be by left view and the row pixel transpostion interval arrangement form 3D rendering of right view.In the 3D rendering to synthesis
When carrying out real-time display, by the display screen of mobile equipment into access customer left eye, the pixel of right view passes through the pixel of left view
The display screen of equipment is moved into the right eye of access customer, and then fusion forms figure of the width with 3D stereoscopic effects in user's brain
Picture.
In addition, it should also be noted that, to realize bore hole 3D display, the display screen of mobile terminal need to lay Grating Film, should
Grating Film can be that slit grating film is alternatively lenticular sheet film.Certainly, user is also wearable realizes bore hole 3D display
Ancillary equipment is to watch stereo display effect.
Obtained multiple view images with parallax can be applied to by the present embodiment two on the basis of above-described embodiment
During synthesis, good image resource is provided for the real-time display of follow-up 3-D view in real time for 3-D view.
Embodiment three
Fig. 4 is a kind of structure of the device for single multiple view images of view video conversion that the embodiment of the present invention three provides
Block diagram.The device can be generally integrated in the mobile terminals such as tablet computer or mobile phone by software and/or hardware realization.Such as Fig. 4
Shown, which includes：Single view image acquiring module 310 and multiple view image determining modules 320.
Wherein, single view image acquiring module 310, for obtaining pending single view image；Multiple view shadows
As determining module 320, for according to default parallax template, determining that pixel is corresponding at least one in the single view image
Offset, and migration processing at least once is carried out to pixel according at least one offset, obtain at least one view
Image.
It is pending single by obtaining an embodiment of the present invention provides a kind of device of two dimensional image conversion 3-D view
View image, and being determined according to default parallax template in single view image after at least one offset of pixel, can be according to
At least one offset carries out migration processing at least once to pixel, obtains at least one view image.Compared with existing
Single view video conversion is had the more of parallax by the realization method that technology provides, technical solution provided in an embodiment of the present invention
During a view image, without obtaining the depth information of image, there are no depth information need to be converted into parallax mapping, fortune
The technical solution that calculation process and calculation amount are provided compared with the prior art is significantly reduced, and is solved in processing capacity
By the limitation that single view video conversion is multiple view images with parallax in limited mobile equipment, for mobile phone or put down
The follow-up real-time display 3-D view of the small mobile terminals such as plate computer provides good image resource, improves user experience.
On the basis of above-described embodiment, the default parallax template is default parallax function or at least one default parallax
Form, for representing that the coordinate value of each pixel need to carry out migration processing with each pixel in the single view image
Relation between offset.
On the basis of above-described embodiment, the multiple view image determining module 320 include offset computation unit and
Multiple view image determination units：Wherein,
The offset computation unit, for according to default parallax function as follows, calculating picture in the single view image
The corresponding at least one offset of vegetarian refreshments：
Offset_ij=F (x, y, σ),
Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in the single view image, and y single regards to be described
The ordinate value for the pixel that the i-th row jth arranges, σ generate the variation coefficient of at least one offset in order to control in figure image；
Offset_ij is the corresponding offset of pixel of the i-th row jth row；
The multiple view image determination unit, for the abscissa value of the pixel in the single view image to be pressed
Migration processing, ordinate value at least once are carried out according at least one offset to remain unchanged, and obtain at least one view shadow
Picture.
On the basis of above-described embodiment, the default parallax template is at least one default parallax form；
Correspondingly, the multiple view image determining module 320 is specifically used for：According to pixel in single view image
Coordinate value inquires about at least one default parallax form, determines the corresponding at least one offset of each pixel, and
Migration processing at least once is carried out to each pixel according at least one offset, obtains at least one view image.
On the basis of above-described embodiment, described device further includes：3-D view generation module, for obtaining at least one
After a view image, the single view image and at least one view image are interleaved processing, formed three-dimensional
Image.
On the basis of above-described embodiment, when generating a view image, then using a view image of generation as
Target view image；
Correspondingly, the 3-D view generation module is specifically used for：By the single view image and target view image
Middle row pixel transpostion interval arrangement, forms stereopsis, for bore hole 3D display.
On the basis of above-described embodiment, the default parallax template is corresponding with the scene of the single view image,
The scene includes personage's scene, landscape scene or moving scene.
The device of the multiple view images of single view video conversion provided in an embodiment of the present invention can perform of the invention arbitrary
The method for the multiple view images of single view video conversion that embodiment is provided, possess the corresponding function module of execution method and
Advantageous effect.The not technical detail of detailed description in the above-described embodiments, reference can be made to the list that any embodiment of the present invention is provided
The method of a multiple view images of view video conversion.
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various apparent variations,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
- A kind of 1. method of the multiple view images of single view video conversion, which is characterized in that the described method includes：Obtain pending single view image；According to default parallax template, the corresponding at least one offset of pixel in the single view image is determined, and according to At least one offset carries out migration processing at least once to pixel, obtains at least one view image.
- 2. according to the method described in claim 1, it is characterized in that, the default parallax template is for default parallax function or at least One default parallax form, for representing in the single view image that the coordinate value of each pixel and each pixel need to be into Relation between the offset of line displacement processing.
- 3. according to the method described in claim 2, it is characterized in that, the default parallax template is default parallax function；Correspondingly, according to default parallax template, the corresponding at least one offset of pixel in the single view image is determined, Including：According to following default parallax function, the corresponding at least one offset of pixel in the single view image is calculated：Offset_ij=F (x, y, σ),Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in the single view image, and y is the single view shadow The ordinate value for the pixel that the i-th row jth arranges, σ generate the variation coefficient of at least one offset in order to control as in；offset_ Ij is the corresponding offset of pixel of the i-th row jth row；Correspondingly, carrying out migration processing at least once to pixel according at least one offset, at least one regard is obtained Figure image, including：The abscissa value of pixel in the single view image is carried out at least once according at least one offset Migration processing, ordinate value remain unchanged, and obtain at least one view image.
- 4. according to the method described in claim 2, it is characterized in that, the default parallax template is at least one default parallax table Lattice；Correspondingly, according to default parallax template, the corresponding at least one offset of pixel in the single view image is determined, And migration processing at least once is carried out to pixel according at least one offset, at least one view image is obtained, is wrapped It includes：According to the coordinate value of pixel in single view image, at least one default parallax form is inquired about, determines each picture The corresponding at least one offset of vegetarian refreshments, and each pixel is carried out at least once according at least one offset Migration processing obtains at least one view image.
- 5. according to the method described in claim 1, it is characterized in that, after at least one view image is obtained, the method It further includes：The single view image and at least one view image are interleaved processing, form 3-D view.
- 6. according to the method described in claim 5, it is characterized in that, when generating a view image, then by one of generation View image is as target view image；Correspondingly, the single view image and at least one view image are interleaved processing, stereopsis is formed, Including：Row pixel transpostion interval in the single view image and target view image is arranged, forms stereopsis, for Bore hole 3D display.
- 7. according to the method described in claim 1, it is characterized in that, the default parallax template and the single view image Scene is corresponding, and the scene includes personage's scene, landscape scene or moving scene.
- 8. a kind of device of the multiple view images of single view video conversion, which is characterized in that including：Single view image acquiring module, for obtaining pending single view image；Multiple view image determining modules, for according to default parallax template, determining pixel pair in the single view image At least one offset answered, and migration processing at least once is carried out to pixel according at least one offset, it obtains At least one view image.
- 9. device according to claim 8, which is characterized in that the default parallax template is default parallax function；Correspondingly, the multiple view image determining module includes offset computation unit and multiple view image determination units, Wherein,The offset computation unit, for according to default parallax function as follows, calculating pixel in the single view image Corresponding at least one offset：Offset_ij=F (x, y, σ),Wherein, x is the abscissa value of the pixel that the i-th row jth arranges in the single view image, and y is the single view shadow The ordinate value for the pixel that the i-th row jth arranges, σ generate the variation coefficient of at least one offset in order to control as in；offset_ Ij is the corresponding offset of pixel of the i-th row jth row；The multiple view image determination unit, for by the abscissa value of the pixel in the single view image according to institute Stating at least one offset progress, migration processing, ordinate value remain unchanged at least once, obtain at least one view image.
- 10. device according to claim 8, which is characterized in that the default parallax template is at least one default parallax Form；Correspondingly, the multiple view image determining module is specifically used for：According to the coordinate value of pixel in single view image, at least one default parallax form is inquired about, determines each picture The corresponding at least one offset of vegetarian refreshments, and each pixel is carried out at least once according at least one offset Migration processing obtains at least one view image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711158453.7A CN108124148A (en) | 2017-11-20 | 2017-11-20 | A kind of method and device of the multiple view images of single view video conversion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711158453.7A CN108124148A (en) | 2017-11-20 | 2017-11-20 | A kind of method and device of the multiple view images of single view video conversion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108124148A true CN108124148A (en) | 2018-06-05 |
Family
ID=62227855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711158453.7A Pending CN108124148A (en) | 2017-11-20 | 2017-11-20 | A kind of method and device of the multiple view images of single view video conversion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108124148A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109672872A (en) * | 2018-12-29 | 2019-04-23 | 合肥工业大学 | A method of naked eye 3D stereoscopic effect is generated with single image |
| CN110007475A (en) * | 2019-04-17 | 2019-07-12 | 万维云视（上海）数码科技有限公司 | Utilize the method and apparatus of virtual depth compensation eyesight |
| CN111193919A (en) * | 2018-11-15 | 2020-05-22 | 中兴通讯股份有限公司 | 3D display method, device, equipment and computer readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1150287A (en) * | 1994-11-11 | 1997-05-21 | 任天堂株式会社 | Stereopicture display device and memory unit used thereof |
| US20090195643A1 (en) * | 2008-02-05 | 2009-08-06 | Disney Enterprises, Inc. | Medial axis decomposition of 2d objects to synthesize binocular depth |
| CN102300105A (en) * | 2010-06-25 | 2011-12-28 | 深圳Tcl新技术有限公司 | Method for converting 2D content into 3D content |
| CN103310477A (en) * | 2013-06-27 | 2013-09-18 | 北京青青树动漫科技有限公司 | Generation method of three-dimensional image |
-
2017
- 2017-11-20 CN CN201711158453.7A patent/CN108124148A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1150287A (en) * | 1994-11-11 | 1997-05-21 | 任天堂株式会社 | Stereopicture display device and memory unit used thereof |
| US20090195643A1 (en) * | 2008-02-05 | 2009-08-06 | Disney Enterprises, Inc. | Medial axis decomposition of 2d objects to synthesize binocular depth |
| CN102300105A (en) * | 2010-06-25 | 2011-12-28 | 深圳Tcl新技术有限公司 | Method for converting 2D content into 3D content |
| CN103310477A (en) * | 2013-06-27 | 2013-09-18 | 北京青青树动漫科技有限公司 | Generation method of three-dimensional image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111193919A (en) * | 2018-11-15 | 2020-05-22 | 中兴通讯股份有限公司 | 3D display method, device, equipment and computer readable medium |
| CN111193919B (en) * | 2018-11-15 | 2023-01-13 | 中兴通讯股份有限公司 | 3D display method, device, equipment and computer readable medium |
| CN109672872A (en) * | 2018-12-29 | 2019-04-23 | 合肥工业大学 | A method of naked eye 3D stereoscopic effect is generated with single image |
| CN110007475A (en) * | 2019-04-17 | 2019-07-12 | 万维云视（上海）数码科技有限公司 | Utilize the method and apparatus of virtual depth compensation eyesight |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4214976B2 (en) | Pseudo-stereoscopic image creation apparatus, pseudo-stereoscopic image creation method, and pseudo-stereoscopic image display system | |
| US7983477B2 (en) | Method and apparatus for generating a stereoscopic image | |
| US20110216160A1 (en) | System and method for creating pseudo holographic displays on viewer position aware devices | |
| US20120293489A1 (en) | Nonlinear depth remapping system and method thereof | |
| WO2003081921A1 (en) | 3-dimensional image processing method and device | |
| CN108833877B (en) | Image processing method and device, computer device and readable storage medium | |
| CN111047709B (en) | Binocular vision naked eye 3D image generation method | |
| US9933626B2 (en) | Stereoscopic image | |
| JP2003284093A (en) | Stereoscopic image processing method and apparatus therefor | |
| US8577202B2 (en) | Method for processing a video data set | |
| US10127714B1 (en) | Spherical three-dimensional video rendering for virtual reality | |
| CN108124148A (en) | A kind of method and device of the multiple view images of single view video conversion | |
| US20210405585A1 (en) | Method and apparatus for processing hologram image data | |
| WO2023169283A1 (en) | Method and apparatus for generating binocular stereoscopic panoramic image, device, storage medium, and product | |
| CN113253845A (en) | View display method, device, medium and electronic equipment based on eye tracking | |
| JP6033625B2 (en) | Multi-viewpoint image generation device, image generation method, display device, program, and recording medium | |
| JP4214529B2 (en) | Depth signal generation device, depth signal generation program, pseudo stereoscopic image generation device, and pseudo stereoscopic image generation program | |
| US9082210B2 (en) | Method and apparatus for adjusting image depth | |
| TWI547904B (en) | Hole filling method for multi-view disparity map | |
| Knorr et al. | An image-based rendering (ibr) approach for realistic stereo view synthesis of tv broadcast based on structure from motion | |
| Knorr et al. | From 2D-to stereo-to multi-view video | |
| KR101794492B1 (en) | System for displaying multiview image | |
| JP4214528B2 (en) | Pseudo stereoscopic image generation apparatus, pseudo stereoscopic image generation program, and pseudo stereoscopic image display system | |
| DE112021003828T5 (en) | Information processing apparatus and image data generation method | |
| JP2003284094A (en) | Stereoscopic image processing method and apparatus therefor |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180605 |