CN110378860A - Method, apparatus, computer equipment and the storage medium of restored video - Google Patents
Method, apparatus, computer equipment and the storage medium of restored video Download PDFInfo
- Publication number
- CN110378860A CN110378860A CN201910692753.6A CN201910692753A CN110378860A CN 110378860 A CN110378860 A CN 110378860A CN 201910692753 A CN201910692753 A CN 201910692753A CN 110378860 A CN110378860 A CN 110378860A
- Authority
- CN
- China
- Prior art keywords
- repaired
- video frame
- algorithm
- image quality
- processing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 149
- 238000012545 processing Methods 0.000 claims abstract description 121
- 230000008439 repair process Effects 0.000 claims abstract description 76
- 230000001771 impaired effect Effects 0.000 claims abstract description 29
- 230000000694 effects Effects 0.000 claims description 87
- 230000000903 blocking effect Effects 0.000 claims description 25
- 238000011946 reduction process Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 18
- 230000003321 amplification Effects 0.000 claims description 16
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 208000003164 Diplopia Diseases 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G06T5/70—
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The disclosure is directed to a kind of method, apparatus of restored video, computer equipment and storage mediums, belong to technical field of video processing.The described method includes: obtaining video frame to be repaired;Determine the image quality damage degree of video frame to be repaired;If the image quality damage degree of video frame to be repaired is more than or equal to default damage degree threshold value, according to the reparation sequence that is badly damaged, restored video frame is treated by least one reparation algorithm and carries out the first repair process;If the image quality damage degree of video frame to be repaired, which is less than, presets damage degree threshold value, according to slight impaired reparation sequence, algorithm is repaired by least one and treats the second repair process of progress of restored video frame.Using the disclosure, after treating restored video frame and distinguishing, algorithm can be repaired by least one and treat the progress repair process of restored video frame according to different reparation sequences, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
Description
Technical field
The disclosure is directed to technical field of video processing, method, apparatus, computer especially with respect to a kind of restored video
Equipment and storage medium.
Background technique
It, all can be inevitably for different factors during being encoded to original video, transmitting encoded video
The image quality of original video is caused to damage.These factors mainly include that blocking artifact, the loss of marginal information, detailed information are lost
Mistake, incorporation of unartificial noise etc..After being decoded to encoded video, the image quality of decoding video is relative to original video
Image quality is poor.
Summary of the invention
In order to overcome the problems, such as that present in the relevant technologies, present disclose provides following technical schemes:
According to the first aspect of the embodiments of the present disclosure, a kind of method of restored video is provided, which comprises
Obtain video frame to be repaired;
Determine the image quality damage degree of the video frame to be repaired;
If the image quality damage degree of the video frame to be repaired is more than or equal to default damage degree threshold value, according to serious
Impaired reparation sequence repairs algorithm by least one and carries out the first repair process to the video frame to be repaired;
If the image quality damage degree of the video frame to be repaired is less than the default damage degree threshold value, according to slight impaired
Reparation sequence repairs algorithm by least one and carries out the second repair process to the video frame to be repaired.
Optionally, the image quality damage degree of the determination video frame to be repaired, comprising:
Determine at least one image quality damage degree algorithm;
The image quality damage degree that the video frame to be repaired is calculated separately by each image quality damage degree algorithm obtains each picture
The corresponding sub- image quality damage degree of matter damage degree algorithm;
Summation is weighted to each sub- image quality damage degree, obtains the image quality damage degree of the video frame to be repaired.
Optionally, described according to the reparation sequence that is badly damaged, algorithm is repaired to the video to be repaired by least one
Frame carries out the first repair process, comprising:
By preset deblocking effect algorithm, deblocking effect processing is carried out to the video frame to be repaired;
After carrying out deblocking effect processing to the video frame to be repaired, by preset super-resolution algorithms, into
Row deblocking effect treated video frame to be repaired amplifies processing according to the first default amplification factor;
To carrying out deblocking effect treated after video frame to be repaired amplifies processing, if amplifying processing
The sharpening degree of video frame to be repaired afterwards is less than default sharpening degree threshold value, then by preset sharpening algorithm, locates to amplifying
Video frame to be repaired after reason is sharpened processing;
After being sharpened processing to the video frame to be repaired that amplifies that treated, if be sharpened, treated
Noise figure in video frame to be repaired is greater than default noise threshold, then by preset noise reduction algorithm, after being sharpened processing
Video frame to be repaired carry out noise reduction process.
Optionally, described according to slight impaired reparation sequence, algorithm is repaired to the video to be repaired by least one
Frame carries out the second repair process, comprising:
By preset super-resolution algorithms, the video frame to be repaired is amplified according to the second default amplification factor
Processing;
After amplifying processing to the video frame to be repaired, by preset deblocking effect algorithm, to putting
Treated greatly, and video frame to be repaired carries out deblocking effect processing;
After carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if carrying out deblocking effect
The sharpening degree for video frame to be repaired that treated is less than default sharpenings degree threshold value, then passes through preset sharpening algorithm, to going
Treated that video frame to be repaired is sharpened processing for blocking artifact;
To carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if being sharpened processing
The noise figure in video frame to be repaired afterwards is greater than default noise threshold, then by preset noise reduction algorithm, locates to being sharpened
Video frame to be repaired after reason carries out noise reduction process.
Optionally, the video format of the affiliated video of video frame to be repaired is yuv format.
According to the second aspect of an embodiment of the present disclosure, a kind of device of restored video is provided, described device includes:
Module is obtained, for obtaining video frame to be repaired;
Determining module, for determining the image quality damage degree of the video frame to be repaired;
Repair module is more than or equal to default damage degree threshold value for the image quality damage degree when the video frame to be repaired
When, according to the reparation sequence that is badly damaged, algorithm is repaired by least one, the first repair place is carried out to the video frame to be repaired
Reason;It is suitable according to slight impaired reparation when the image quality damage degree of the video frame to be repaired is less than the default damage degree threshold value
Sequence repairs algorithm by least one and carries out the second repair process to the video frame to be repaired.
Optionally, the determining module, is used for:
Determine at least one image quality damage degree algorithm;
The image quality damage degree that the video frame to be repaired is calculated separately by each image quality damage degree algorithm obtains each picture
The corresponding sub- image quality damage degree of matter damage degree algorithm;
Summation is weighted to each sub- image quality damage degree, obtains the image quality damage degree of the video frame to be repaired.
Optionally, the repair module, is used for:
By preset deblocking effect algorithm, deblocking effect processing is carried out to the video frame to be repaired;
After carrying out deblocking effect processing to the video frame to be repaired, by preset super-resolution algorithms, into
Row deblocking effect treated video frame to be repaired amplifies processing according to the first default amplification factor;
To carrying out deblocking effect treated after video frame to be repaired amplifies processing, if amplifying processing
The sharpening degree of video frame to be repaired afterwards is less than default sharpening degree threshold value, then by preset sharpening algorithm, locates to amplifying
Video frame to be repaired after reason is sharpened processing;
After being sharpened processing to the video frame to be repaired that amplifies that treated, if be sharpened, treated
Noise figure in video frame to be repaired is greater than default noise threshold, then by preset noise reduction algorithm, after being sharpened processing
Video frame to be repaired carry out noise reduction process.
Optionally, the repair module, is used for:
By preset super-resolution algorithms, the video frame to be repaired is amplified according to the second default amplification factor
Processing;
After amplifying processing to the video frame to be repaired, by preset deblocking effect algorithm, to putting
Treated greatly, and video frame to be repaired carries out deblocking effect processing;
After carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if carrying out deblocking effect
The sharpening degree for video frame to be repaired that treated is less than default sharpenings degree threshold value, then passes through preset sharpening algorithm, to going
Treated that video frame to be repaired is sharpened processing for blocking artifact;
To carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if being sharpened processing
The noise figure in video frame to be repaired afterwards is greater than default noise threshold, then by preset noise reduction algorithm, locates to being sharpened
Video frame to be repaired after reason carries out noise reduction process.
Optionally, the video format of the affiliated video of video frame to be repaired is yuv format.
According to the third aspect of an embodiment of the present disclosure, a kind of computer equipment is provided, the computer equipment includes processing
Device, communication interface, memory and communication bus, in which:
The processor, the communication interface and the memory complete mutual communication by the communication bus;
The memory, for storing computer program;
The processor, the method for executing the program stored on the memory, to realize above-mentioned restored video.
According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, it is described computer-readable
Computer program is stored in storage medium, the computer program realizes the side of above-mentioned restored video when being executed by processor
Method.
The technical scheme provided by this disclosed embodiment can include the following benefits:
In the embodiments of the present disclosure, repair process can be carried out to any video frame to be repaired, the video frame repaired
The image quality of the more preprosthetic video frame of image quality increases.Meanwhile the embodiment of the present disclosure is also based on different videos to be repaired
The image quality damage degree of frame is treated restored video frame and is distinguished, if image quality damage degree is higher, video frame to be repaired is serious
Impaired video frame, if image quality damage degree is lower, video frame to be repaired is slightly impaired video frame.To view to be repaired
After frequency frame distinguishes, can according to different reparation sequences, by least one repair algorithm treat restored video frame into
Row repair process, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.In the accompanying drawings:
Fig. 1 is a kind of structural schematic diagram of the system of restored video shown according to an exemplary embodiment;
Fig. 2 is a kind of structural schematic diagram of the device of restored video shown according to an exemplary embodiment;
Fig. 3 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 4 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 5 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 6 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 7 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 8 is a kind of flow diagram of the method for restored video shown according to an exemplary embodiment;
Fig. 9 is a kind of structural schematic diagram of the device of restored video shown according to an exemplary embodiment;
Figure 10 is a kind of structural schematic diagram of computer equipment shown according to an exemplary embodiment.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
The embodiment of the present disclosure provides a kind of method of restored video, and this method can be realized by computer equipment.One
In the possible implementation of kind, in a kind of system of restored video, as shown in Figure 1, video server can be set, repaired
Video server and terminal, video server, restored video server, terminal number can be it is multiple, the disclosure reality
It applies in example and is illustrated by taking a video server, a restored video server and a terminal as an example.In video server
In, it can store a large amount of video, these videos may there are the feelings that light or heavy image quality is damaged for different factors
Condition.It is appreciated if the video that image quality damage situations directly will be present directly is shared to terminal for user, user experience, shadow can be reduced
Viewing effect is rung, therefore before the video sharing to terminal that image quality damage situations will be present, video server can will be any
Video to be repaired is sent to restored video server, and restored video server can carry out repair place to any video to be repaired
Reason.After restored video server carries out repair process to any video to be repaired, restored video server can will be carried out
Restored video after repair process is shared to terminal to be appreciated for user, and user experience can be improved in this way, improve viewing quality.
In restored video server, video repair process frame can be set.As shown in Fig. 2, video repair process
Frame may include video input module, decoder module, source analysis module, pre-processing module, coding module, video output mould
Block.The method for the restored video that the embodiment of the present disclosure provides, can execute in above-mentioned pre-processing module.
Decoder module can be used for being decoded encoded video, and obtaining YUV, (a kind of colour coding method, " Y " indicate bright
Brightness Luminance, " U " and " V " indicate chrominance C hrominance) format decoding video.Source analysis module can be used for pair
The essential attribute of video, high-level semantics and high-order feature are analyzed, preferably to determine the characteristic of video itself, and then can be with
Other modules are assisted to play the maximum effectiveness of other modules.Pre-processing module can be used for through image or video processing technique pair
The video of yuv format carries out data mart modeling, makes the subjective vision effect of the video after processing towards the appreciable direction of human eye, picture
Advance in the direction in the direction and picture quality enhancement that matter is improved.Coding module can be used for pressing the video of yuv format
Contracting, obtains encoded video, so that the data volume of encoded video is far smaller than the data volume of original video, in this way in transmission coding view
During frequency, bandwidth consumption can be saved, is convenient for network transmission.Video Output Modules be commonly used for output resolution ratio and
The identical video of the resolution ratio of original video, but in the embodiments of the present disclosure, Video Output Modules can be used for exporting resolution
The problem of rate is greater than the video of the resolution ratio of original video, can solve loss in detail in video in this way, by introducing super-resolution
Rate submodule improves the resolution ratio of original video, and the specific final resolution ratio of video depends in super-resolution submodule
The amplification factor of setting.
An exemplary embodiment of the present disclosure provides a kind of methods of restored video, as shown in figure 3, the processing stream of this method
Journey may include following step:
Step S301 obtains video frame to be repaired.
In an implementation, the available video frame to be repaired of computer equipment, video frame to be repaired can be video to be repaired
In a video frame, each video to be repaired can include multiple video frames.Optionally, the affiliated video of video frame to be repaired
Video format can be yuv format.
Step S302 determines the image quality damage degree of video frame to be repaired.
In an implementation, computer equipment can calculate the image quality damage degree of video frame to be repaired.The image quality of restored video frame
Damage degree can reflect the severity of the blocking artifact of video frame to be repaired.It can be expressed by F (I)=Score_block
Formula indicates the image quality damage degree of video frame to be repaired, wherein Score_block is the image quality damage degree of video frame to be repaired, letter
Number F can indicate one or more kinds of image quality damage degree algorithms.In practical application, different image quality damage degree algorithms can be from difference
It is evaluated with reference to image quality damage degree of the angle to video frame, evaluation effect is different, a kind of image quality damage degree algorithm can be chosen,
The image quality damage degree for calculating video frame to be repaired can choose a variety of image quality damage degree algorithms, calculate video frame to be repaired jointly
Image quality damage degree.
Optionally, step S302 may include: to determine at least one image quality damage degree algorithm;It is calculated by each image quality damage degree
Method calculates separately the image quality damage degree of video frame to be repaired, and it is impaired to obtain the corresponding sub- image quality of each image quality damage degree algorithm
Degree;Summation is weighted to each sub- image quality damage degree, obtains the image quality damage degree of video frame to be repaired.
In an implementation, the image quality damage degree of video frame to be repaired is calculated jointly by choosing a variety of image quality damage degree algorithms,
It can be evaluated from multiple with reference to image quality damage degree of the angle to video frame, the effect of different evaluation mode can be integrated in this way
Fruit.Computer equipment can determine at least one image quality damage degree algorithm, be calculated separately by each image quality damage degree algorithm to be repaired
The image quality damage degree of multiple video frame, obtains the corresponding sub- image quality damage degree of each image quality damage degree algorithm, to each sub- image quality by
Damage degree is weighted summation, obtains the image quality damage degree of video frame to be repaired.Wherein, the corresponding power of different image quality damage degree algorithms
Weight, can be set according to demand.
Step S303, the image quality damage degree based on video frame to be repaired, judge video frame to be repaired be badly damaged or
It is slight impaired.
In an implementation, as shown in figure 4, image quality analysis module can be set in computer equipment, image quality analysis module can
With the image quality damage degree based on video frame to be repaired, judge that video frame to be repaired is either slight is damaged that be badly damaged.If
Video frame to be repaired is to be badly damaged, then is input to be badly damaged video frame to be repaired in repair module and carries out repair process,
If video frame to be repaired is slightly to be damaged, video frame to be repaired is input in slightly impaired repair module and carries out repair place
Reason.
Step S304, if the image quality damage degree of video frame to be repaired is more than or equal to default damage degree threshold value, to
Restored video frame is to be badly damaged, and according to the reparation sequence that is badly damaged, repairs algorithm by least one and treats restored video frame
Carry out the first repair process.
Step S305, if the image quality damage degree of video frame to be repaired is less than default damage degree threshold value, video to be repaired
Frame is slightly to be damaged, and according to slight impaired reparation sequence, treats restored video frame progress second by least one reparation algorithm
Repair process.
In an implementation, video frame to be repaired is when being badly damaged either slight impaired, and the corresponding at least one used is repaired
Double calculation method can be the same or different, but treat the progress repair process of restored video frame repairing algorithm using at least one
During, different using the sequence for repairing algorithm progress repair process, different impaired journeys can be discussed in detail in latter embodiments
The sequence of the different repair processes of the video frame to be repaired of degree.
In the embodiments of the present disclosure, repair process can be carried out to any video frame to be repaired, the video frame repaired
The image quality of the more preprosthetic video frame of image quality increases.Meanwhile the embodiment of the present disclosure is also based on different videos to be repaired
The image quality damage degree of frame is treated restored video frame and is distinguished, if image quality damage degree is higher, video frame to be repaired is serious
Impaired video frame, if image quality damage degree is lower, video frame to be repaired is slightly impaired video frame.To view to be repaired
After frequency frame distinguishes, can according to different reparation sequences, by least one repair algorithm treat restored video frame into
Row repair process, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
Based on identical inventive concept, an exemplary embodiment of the present disclosure provides a kind of methods of restored video, such as Fig. 5
Shown, the process flow of this method may include following step:
Step S501 obtains video frame to be repaired.
In an implementation, the available video frame to be repaired of computer equipment, video frame to be repaired can be video to be repaired
In a video frame, each video to be repaired can include multiple video frames.Optionally, the affiliated video of video frame to be repaired
Video format can be yuv format.
Step S502 determines the image quality damage degree of video frame to be repaired.
In an implementation, computer equipment can calculate the image quality damage degree of video frame to be repaired.The image quality of restored video frame
Damage degree can reflect the severity of the blocking artifact of video frame to be repaired.It can be expressed by F (I)=Score_block
Formula indicates the image quality damage degree of video frame to be repaired, wherein Score_block is the image quality damage degree of video frame to be repaired, letter
Number F can indicate one or more kinds of image quality damage degree algorithms.In practical application, different image quality damage degree algorithms can be from difference
It is evaluated with reference to image quality damage degree of the angle to video frame, evaluation effect is different, a kind of image quality damage degree algorithm can be chosen,
The image quality damage degree for calculating video frame to be repaired can choose a variety of image quality damage degree algorithms, calculate video frame to be repaired jointly
Image quality damage degree.
Step S503, if the image quality damage degree of video frame to be repaired is more than or equal to default damage degree threshold value, really
Fixed video frame to be repaired is to be badly damaged.
In an implementation, if it is determined that video frame to be repaired is to be badly damaged, and can repair algorithm by least one and treat
Restored video frame carries out the first repair process, wherein it may include deblocking effect algorithm, super-resolution that at least one, which repairs algorithm,
Algorithm, sharpening algorithm, noise reduction algorithm, the algorithm that they are corresponding in turn to can be denoted as AR algorithm, SR algorithm, MS algorithm, DE algorithm.
Step S504 treats restored video frame and carries out deblocking effect processing by preset deblocking effect algorithm.
In an implementation, as shown in fig. 6, the video frame to be repaired that the video of the available yuv format of computer equipment includes
A can remove the blocking artifact in video frame A to be repaired using AR algorithm, obtain video frame B to be repaired.
Step S505, after treating restored video frame and carrying out deblocking effect processing, by preset super-resolution algorithms,
Processing is amplified according to the first default amplification factor to deblocking effect treated video frame to be repaired is carried out.
In an implementation, SR algorithm can be used, restored video frame B is treated and amplifies processing, obtain video frame to be repaired
C.Amplification factor can be scale, and scale can be set to 1, may be set to be the numerical value greater than 1.If scale is arranged
It is 1, then can is video frame B to be repaired without enhanced processing, video frame C to be repaired.Restored video frame B is treated if necessary
Processing is amplified, then can set scale to the numerical value such as 2,3.
Step S506, to carrying out deblocking effect treated after video frame to be repaired amplifies processing, if into
The sharpening degree of video frame to be repaired after row enhanced processing is less than default sharpening degree threshold value, then right by preset sharpening algorithm
Amplifying treated, video frame to be repaired is sharpened processing.
In an implementation, MS algorithm can be used, restored video frame C is treated and is sharpened processing, obtain video frame to be repaired
D.It is possible, firstly, to the sharpening degree of video frame C to be repaired be judged, if the sharpening degree of video frame C to be repaired is more than or equal in advance
It then can be video frame C to be repaired without Edge contrast, video frame D to be repaired if sharpening degree threshold value thr_sharp.If
The sharpening degree of video frame C to be repaired is less than thr_sharp, then can use MS algorithm, treat restored video frame C and be sharpened place
Reason.Sharpening degree can be indicated by G (I)=Score_sharp expression formula, wherein Score_sharp is video frame C to be repaired
Sharpening degree.
Step S507, after being sharpened processing to the video frame to be repaired that amplifies that treated, if carried out sharp
Change the noise figure in treated video frame to be repaired and be greater than default noise threshold, then by preset noise reduction algorithm, to progress
Video frame to be repaired after Edge contrast carries out noise reduction process.
In an implementation, DE algorithm can be used, restored video frame D is treated and carries out noise reduction process, obtain video frame to be repaired
E.It is possible, firstly, to the noise figure of video frame E to be repaired be judged, if the noise figure of video frame E to be repaired is less than or equal in advance
It then can be video frame D to be repaired without Edge contrast, video frame E to be repaired if noise threshold thr_noise.If to
The noise figure of restored video frame D is greater than thr_noise, then can use DE algorithm, treats restored video frame D and carries out at noise reduction
Reason.Noise figure can be indicated by N (I)=Score_noise expression formula, wherein Score_noise is video frame D to be repaired
Level of noise.
In above process, deblocking effect algorithm can erase some details in script video frame, super-resolution algorithms
Can subsidiary details in the video frame, video frame is amplified, but noise can be also amplified simultaneously.Severe is damaged
Video frame to be repaired, i.e., the bigger video frame of existing blocking artifact, they visually seem to have can be apparent horse
The quantity of Sai Ke or mosaic is relatively more.For this video frame to be repaired, deblocking effect algorithm can be first passed through, to be repaired
Blocking artifact in multiple video frame reduces, such as can reduce the quantity of mosaic or eliminate mosaic, then passes through oversubscription again
Resolution algorithm subsidiary details in carrying out deblocking effect treated video frame to be repaired.Otherwise, if first carrying out super-resolution
Processing, is similar to treat restored video frame and amplifies processing, then the serious blocking artifact of script can be in video frame to be repaired
Amplification, the blocking artifact in video frame to be repaired after carrying out super-resolution processing can be more obvious, and specific manifestation can be Marseille
It is gram even more serious.It is subsequent, it needs to remove in the video frame to be repaired after carrying out super-resolution processing by deblocking effect algorithm
It is clean to be difficult to the comparison for going blocking artifact by deblocking effect algorithm at this time for more serious blocking artifact.In addition, if diplopia to be repaired
The blocking artifact of frequency frame script is bigger, the block for same deblocking effect algorithm, in the smaller video frame of removal size
The effect of blocking artifact in the effect of the effect video frame more bigger than removal size is more preferable, therefore removal is being surpassed as far as possible
The effect of video frame to be repaired before resolution processes can be much better.
In addition, by Edge contrast, can by the edge reparation of video frame to be repaired it is sharper keen, be more clear, take turns
Profile item is more more obvious, and still, while being sharpened to edge, noise can be also sharpened, therefore in disclosure reality
Applying in example to be first sharpened, then carries out noise reduction, during noise reduction process, inevitably remove one in video frame
A little details.
By taking the texture on clothes as an example, the texture of clothes can be considered as a kind of marginal information, if first to the line of clothes
Reason carries out noise reduction process, then the texture for getting rid of clothes that can be more or less, though behind the texture of clothes is sharpened again,
The texture for the clothes got rid of also is mended not back.If the texture of clothes is all removed, can not carry out sharp yet
Change the object of processing.But if being first sharpened processing to the texture of clothes, it can retain and reinforce the line of clothes
Reason.It is subsequent to pass through before noise reduction process removal sharpening and making an uproar after sharpening although noise is also sharpened at this time
Sound.
In the embodiments of the present disclosure, repair process can be carried out to any video frame to be repaired, the video frame repaired
The image quality of the more preprosthetic video frame of image quality increases.Meanwhile the embodiment of the present disclosure is also based on different videos to be repaired
The image quality damage degree of frame is treated restored video frame and is distinguished, if image quality damage degree is higher, video frame to be repaired is serious
Impaired video frame, if image quality damage degree is lower, video frame to be repaired is slightly impaired video frame.To view to be repaired
After frequency frame distinguishes, can according to different reparation sequences, by least one repair algorithm treat restored video frame into
Row repair process, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
Based on identical inventive concept, an exemplary embodiment of the present disclosure provides a kind of methods of restored video, such as Fig. 7
Shown, the process flow of this method may include following step:
Step S701 obtains video frame to be repaired.
In an implementation, the available video frame to be repaired of computer equipment, video frame to be repaired can be video to be repaired
In a video frame, each video to be repaired can include multiple video frames.Optionally, the affiliated video of video frame to be repaired
Video format can be yuv format.
Step S702 determines the image quality damage degree of video frame to be repaired.
In an implementation, computer equipment can calculate the image quality damage degree of video frame to be repaired.The image quality of restored video frame
Damage degree can reflect the severity of the blocking artifact of video frame to be repaired.It can be expressed by F (I)=Score_block
Formula indicates the image quality damage degree of video frame to be repaired, wherein Score_block is the image quality damage degree of video frame to be repaired, letter
Number F can indicate one or more kinds of image quality damage degree algorithms.In practical application, different image quality damage degree algorithms can be from difference
It is evaluated with reference to image quality damage degree of the angle to video frame, evaluation effect is different, a kind of image quality damage degree algorithm can be chosen,
The image quality damage degree for calculating video frame to be repaired can choose a variety of image quality damage degree algorithms, calculate video frame to be repaired jointly
Image quality damage degree.
Step S703, if the image quality damage degree of video frame to be repaired is less than default damage degree threshold value, it is determined that be repaired
Video frame is slight impaired.
In an implementation, if it is determined that video frame to be repaired is slightly to be damaged, and can repair algorithm by least one and treat
Restored video frame carries out the second repair process, wherein it may include deblocking effect algorithm, super-resolution that at least one, which repairs algorithm,
Algorithm, sharpening algorithm, noise reduction algorithm, the algorithm that they are corresponding in turn to can be denoted as AR algorithm, SR algorithm, MS algorithm, DE algorithm.
Step S704, by preset super-resolution algorithms, treat restored video frame according to the second default amplification factor into
Row enhanced processing.
In an implementation, as shown in figure 8, the video frame to be repaired that the video of the available yuv format of computer equipment includes
A can use SR algorithm, treat restored video frame A and amplify processing, obtain video frame B to be repaired.Amplification factor can be
Scale, scale can be set to 1, may be set to be the numerical value greater than 1.It, can be without if scale is set as 1
Enhanced processing, video frame B to be repaired are video frame A to be repaired.Restored video frame A is treated if necessary and amplifies processing, then
It can set scale to the numerical value such as 2,3.
Step S705, after treating restored video frame and amplifying processing, by preset deblocking effect algorithm, into
Video frame to be repaired after row enhanced processing carries out deblocking effect processing.
In an implementation, the blocking artifact in video frame B to be repaired can be removed using AR algorithm, obtains video frame C to be repaired.
Step S706, after carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if into
The sharpening degree of row deblocking effect treated video frame to be repaired is less than default sharpenings degree threshold value, then passes through preset sharpening calculation
Method, to deblocking effect is carried out, treated that video frame to be repaired is sharpened processing.
In an implementation, MS algorithm can be used, restored video frame C is treated and is sharpened processing, obtain video frame to be repaired
D.It is possible, firstly, to the sharpening degree of video frame C to be repaired be judged, if the sharpening degree of video frame C to be repaired is more than or equal in advance
It then can be video frame C to be repaired without Edge contrast, video frame D to be repaired if sharpening degree threshold value thr_sharp.If
The sharpening degree of video frame C to be repaired is less than thr_sharp, then can use MS algorithm, treat restored video frame C and be sharpened place
Reason.Sharpening degree can be indicated by G (I)=Score_sharp expression formula, wherein Score_sharp is video frame C to be repaired
Sharpening degree.
Step S707, to carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if into
The noise figure in video frame to be repaired after row Edge contrast is greater than default noise threshold, then right by preset noise reduction algorithm
Being sharpened treated, video frame to be repaired carries out noise reduction process.
In an implementation, DE algorithm can be used, restored video frame D is treated and carries out noise reduction process, obtain video frame to be repaired
E.It is possible, firstly, to the noise figure of video frame E to be repaired be judged, if the noise figure of video frame E to be repaired is less than or equal in advance
It then can be video frame D to be repaired without Edge contrast, video frame E to be repaired if noise threshold thr_noise.If to
The noise figure of restored video frame D is greater than thr_noise, then can use DE algorithm, treats restored video frame D and carries out at noise reduction
Reason.Noise figure can be indicated by N (I)=Score_noise expression formula, wherein Score_noise is video frame D to be repaired
Level of noise.
In above process, deblocking effect algorithm can erase some details in script video frame, super-resolution algorithms
Can subsidiary details in the video frame, video frame is amplified, but noise can be also amplified simultaneously.For slightly impaired
Video frame to be repaired, i.e., the smaller video frame of existing blocking artifact, can first carry out super-resolution processing, due to diplopia to be repaired
The blocking artifact of script is smaller in frequency frame, therefore even if will not obviously aggravate diplopia to be repaired first to super-resolution processing is first carried out
Blocking artifact in frequency frame.After treating restored video frame and carrying out superresolution processing, it can achieve and mended in video frame to be repaired
Fill the effect of details.Then, the video frame to be repaired after progress superresolution processing can be gone by deblocking effect algorithm
Blocking artifact processing.Although deblocking effect algorithm can erase some details in script video frame, super due to first passing through in advance
Resolution processes supplement a large amount of details in video frame to be repaired, so even if going in deblocking effect treatment process
Remove it is some progress superresolution processings after video frame to be repaired in details, can finally be able to the details remained compared with into
Video frame before row repair process or very much.
Conversely, for slightly impaired video frame to be repaired, their image quality relatively preferably, details relative abundance.If
Deblocking effect processing is first carried out, then carries out super-resolution processing, deblocking effect processing then can be by slightly impaired video to be repaired
Script details abundant is smeared smooth in frame, will increase the difficulty that super-resolution processing restores the details of video frame in the process in this way
Degree.I.e. for slightly impaired video frame to be repaired, subtraction is first done, then do addition, income effect is undesirable.Because image quality is preferable
Video frame, what is be more concerned about during repair process is the increase of details.And the blocking artifact of the preferable video frame of image quality itself
Natively small, spectators would not be too obvious to the visual perception of blocking artifact.
In addition, by Edge contrast, can by the edge reparation of video frame to be repaired it is sharper keen, be more clear, take turns
Profile item is more more obvious, and still, while being sharpened to edge, noise can be also sharpened, therefore in disclosure reality
Applying in example to be first sharpened, then carries out noise reduction, during noise reduction process, inevitably remove one in video frame
A little details.
By taking the texture on clothes as an example, the texture of clothes can be considered as a kind of marginal information, if first to the line of clothes
Reason carries out noise reduction process, then the texture for getting rid of clothes that can be more or less, though behind the texture of clothes is sharpened again,
The texture for the clothes got rid of also is mended not back.If the texture of clothes is all removed, can not carry out sharp yet
Change the object of processing.But if being first sharpened processing to the texture of clothes, it can retain and reinforce the line of clothes
Reason.It is subsequent to pass through before noise reduction process removal sharpening and making an uproar after sharpening although noise is also sharpened at this time
Sound.
In the embodiments of the present disclosure, repair process can be carried out to any video frame to be repaired, the video frame repaired
The image quality of the more preprosthetic video frame of image quality increases.Meanwhile the embodiment of the present disclosure is also based on different videos to be repaired
The image quality damage degree of frame is treated restored video frame and is distinguished, if image quality damage degree is higher, video frame to be repaired is serious
Impaired video frame, if image quality damage degree is lower, video frame to be repaired is slightly impaired video frame.To view to be repaired
After frequency frame distinguishes, can according to different reparation sequences, by least one repair algorithm treat restored video frame into
Row repair process, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
Disclosure another exemplary embodiment provides a kind of device of restored video, as shown in figure 9, the device includes:
Module 910 is obtained, for obtaining video frame to be repaired;
Determining module 920, for determining the image quality damage degree of the video frame to be repaired;
Repair module 930 is more than or equal to default damage degree for the image quality damage degree when the video frame to be repaired
When threshold value, according to the reparation sequence that is badly damaged, algorithm is repaired by least one, the video frame progress first to be repaired is repaired
Multiple processing;When the image quality damage degree of the video frame to be repaired is less than the default damage degree threshold value, repaired according to slight be damaged
Multiple sequence repairs algorithm by least one and carries out the second repair process to the video frame to be repaired.
Optionally, the determining module 920, is used for:
Determine at least one image quality damage degree algorithm;
The image quality damage degree that the video frame to be repaired is calculated separately by each image quality damage degree algorithm obtains each picture
The corresponding sub- image quality damage degree of matter damage degree algorithm;
Summation is weighted to each sub- image quality damage degree, obtains the image quality damage degree of the video frame to be repaired.
Optionally, the repair module 930, is used for:
By preset deblocking effect algorithm, deblocking effect processing is carried out to the video frame to be repaired;
After carrying out deblocking effect processing to the video frame to be repaired, by preset super-resolution algorithms, into
Row deblocking effect treated video frame to be repaired amplifies processing according to the first default amplification factor;
To carrying out deblocking effect treated after video frame to be repaired amplifies processing, if amplifying processing
The sharpening degree of video frame to be repaired afterwards is less than default sharpening degree threshold value, then by preset sharpening algorithm, locates to amplifying
Video frame to be repaired after reason is sharpened processing;
After being sharpened processing to the video frame to be repaired that amplifies that treated, if be sharpened, treated
Noise figure in video frame to be repaired is greater than default noise threshold, then by preset noise reduction algorithm, after being sharpened processing
Video frame to be repaired carry out noise reduction process.
Optionally, the repair module 930, is used for:
By preset super-resolution algorithms, the video frame to be repaired is amplified according to the second default amplification factor
Processing;
After amplifying processing to the video frame to be repaired, by preset deblocking effect algorithm, to putting
Treated greatly, and video frame to be repaired carries out deblocking effect processing;
After carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if carrying out deblocking effect
The sharpening degree for video frame to be repaired that treated is less than default sharpenings degree threshold value, then passes through preset sharpening algorithm, to going
Treated that video frame to be repaired is sharpened processing for blocking artifact;
To carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if being sharpened processing
The noise figure in video frame to be repaired afterwards is greater than default noise threshold, then by preset noise reduction algorithm, locates to being sharpened
Video frame to be repaired after reason carries out noise reduction process.
Optionally, the video format of the affiliated video of video frame to be repaired is yuv format.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
In the embodiments of the present disclosure, repair process can be carried out to any video frame to be repaired, the video frame repaired
The image quality of the more preprosthetic video frame of image quality increases.Meanwhile the embodiment of the present disclosure is also based on different videos to be repaired
The image quality damage degree of frame is treated restored video frame and is distinguished, if image quality damage degree is higher, video frame to be repaired is serious
Impaired video frame, if image quality damage degree is lower, video frame to be repaired is slightly impaired video frame.To view to be repaired
After frequency frame distinguishes, can according to different reparation sequences, by least one repair algorithm treat restored video frame into
Row repair process, repair process is more targeted, and the image quality of the obtained video frame repaired is higher.
It should be understood that the device of restored video provided by the above embodiment is in restored video, only with above-mentioned each function
Can module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different functions
Module is completed, i.e., the internal structure of computer equipment is divided into different functional modules, with complete it is described above whole or
Person's partial function.In addition, the device of restored video provided by the above embodiment and the embodiment of the method for restored video belong to it is same
Design, specific implementation process are detailed in embodiment of the method, and which is not described herein again.
Figure 10 shows the structural schematic diagram of the computer equipment 1900 of one exemplary embodiment of disclosure offer.The meter
Bigger difference can be generated because configuration or performance are different by calculating machine equipment 1900, may include one or more processors
(central processing units, CPU) 1910 and one or more memory 1920.Wherein, the storage
At least one instruction is stored in device 1920, at least one instruction is loaded by the processor 1910 and executed on to realize
The method for stating restored video described in embodiment.
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are wanted by right
It asks and points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (10)
1. a kind of method of restored video, which is characterized in that the described method includes:
Obtain video frame to be repaired;
Determine the image quality damage degree of the video frame to be repaired;
If the image quality damage degree of the video frame to be repaired is more than or equal to default damage degree threshold value, according to being badly damaged
Reparation sequence repairs algorithm by least one and carries out the first repair process to the video frame to be repaired;
If the image quality damage degree of the video frame to be repaired is less than the default damage degree threshold value, according to slight impaired reparation
Sequentially, algorithm is repaired by least one and the second repair process is carried out to the video frame to be repaired.
2. the method according to claim 1, wherein the image quality of the determination video frame to be repaired is impaired
Degree, comprising:
Determine at least one image quality damage degree algorithm;
The image quality damage degree that the video frame to be repaired is calculated separately by each image quality damage degree algorithm, obtain each image quality by
The corresponding sub- image quality damage degree of damage degree algorithm;
Summation is weighted to each sub- image quality damage degree, obtains the image quality damage degree of the video frame to be repaired.
3. the method according to claim 1, wherein it is described according to be badly damaged reparation sequence, pass through at least one
Kind repairs algorithm and carries out the first repair process to the video frame to be repaired, comprising:
By preset deblocking effect algorithm, deblocking effect processing is carried out to the video frame to be repaired;
After carrying out deblocking effect processing to the video frame to be repaired, by preset super-resolution algorithms, to going
Blocking artifact treated video frame to be repaired amplifies processing according to the first default amplification factor;
To carrying out deblocking effect treated after video frame to be repaired amplifies processing, if amplified, treated
The sharpening degree of video frame to be repaired is less than default sharpening degree threshold value, then by preset sharpening algorithm, after amplifying processing
Video frame to be repaired be sharpened processing;
After being sharpened processing to the video frame to be repaired that amplifies that treated, if it is to be repaired to be sharpened that treated
Noise figure in multiple video frame is greater than default noise threshold, then by preset noise reduction algorithm, to be sharpened that treated to
Restored video frame carries out noise reduction process.
4. passing through at least one the method according to claim 1, wherein described be damaged reparation sequence according to slight
Kind repairs algorithm and carries out the second repair process to the video frame to be repaired, comprising:
By preset super-resolution algorithms, place is amplified according to the second default amplification factor to the video frame to be repaired
Reason;
After amplifying processing to the video frame to be repaired, by preset deblocking effect algorithm, locate to amplifying
Video frame to be repaired after reason carries out deblocking effect processing;
After carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if carrying out deblocking effect processing
The sharpening degree of video frame to be repaired afterwards is less than default sharpening degree threshold value, then by preset sharpening algorithm, to progress deblocking effect
Answering treated, video frame to be repaired is sharpened processing;
To carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if be sharpened, treated
Noise figure in video frame to be repaired is greater than default noise threshold, then by preset noise reduction algorithm, after being sharpened processing
Video frame to be repaired carry out noise reduction process.
5. method according to any of claims 1-4, which is characterized in that the affiliated video of video frame to be repaired
Video format is yuv format.
6. a kind of device of restored video, which is characterized in that described device includes:
Module is obtained, for obtaining video frame to be repaired;
Determining module, for determining the image quality damage degree of the video frame to be repaired;
Repair module, for when the image quality damage degree of the video frame to be repaired is more than or equal to default damage degree threshold value,
According to the reparation sequence that is badly damaged, algorithm is repaired by least one, the first repair process is carried out to the video frame to be repaired;
When the image quality damage degree of the video frame to be repaired is less than the default damage degree threshold value, sequentially according to slight impaired reparation,
Algorithm is repaired by least one, and the second repair process is carried out to the video frame to be repaired.
7. device according to claim 6, which is characterized in that the repair module is used for:
By preset deblocking effect algorithm, deblocking effect processing is carried out to the video frame to be repaired;
After carrying out deblocking effect processing to the video frame to be repaired, by preset super-resolution algorithms, to going
Blocking artifact treated video frame to be repaired amplifies processing according to the first default amplification factor;
To carrying out deblocking effect treated after video frame to be repaired amplifies processing, if amplified, treated
The sharpening degree of video frame to be repaired is less than default sharpening degree threshold value, then by preset sharpening algorithm, after amplifying processing
Video frame to be repaired be sharpened processing;
After being sharpened processing to the video frame to be repaired that amplifies that treated, if it is to be repaired to be sharpened that treated
Noise figure in multiple video frame is greater than default noise threshold, then by preset noise reduction algorithm, to be sharpened that treated to
Restored video frame carries out noise reduction process.
8. device according to claim 6, which is characterized in that the repair module is used for:
By preset super-resolution algorithms, place is amplified according to the second default amplification factor to the video frame to be repaired
Reason;
After amplifying processing to the video frame to be repaired, by preset deblocking effect algorithm, locate to amplifying
Video frame to be repaired after reason carries out deblocking effect processing;
After carrying out deblocking effect processing to the video frame to be repaired that amplifies that treated, if carrying out deblocking effect processing
The sharpening degree of video frame to be repaired afterwards is less than default sharpening degree threshold value, then by preset sharpening algorithm, to progress deblocking effect
Answering treated, video frame to be repaired is sharpened processing;
To carrying out deblocking effect treated after video frame to be repaired is sharpened processing, if be sharpened, treated
Noise figure in video frame to be repaired is greater than default noise threshold, then by preset noise reduction algorithm, after being sharpened processing
Video frame to be repaired carry out noise reduction process.
9. a kind of computer equipment, which is characterized in that the computer equipment includes processor, communication interface, memory and leads to
Believe bus, in which:
The processor, the communication interface and the memory complete mutual communication by the communication bus;
The memory, for storing computer program;
The processor, for executing the program stored on the memory, to realize any side claim 1-5
Method step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program realizes claim 1-5 any method and step when the computer program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910692753.6A CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910692753.6A CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110378860A true CN110378860A (en) | 2019-10-25 |
CN110378860B CN110378860B (en) | 2023-08-18 |
Family
ID=68256921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910692753.6A Active CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110378860B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113507625A (en) * | 2021-06-22 | 2021-10-15 | 西安理工大学 | Self-adaptive video restoration method |
CN114501139A (en) * | 2022-03-31 | 2022-05-13 | 深圳思谋信息科技有限公司 | Video processing method and device, computer equipment and storage medium |
CN115082357A (en) * | 2022-07-20 | 2022-09-20 | 深圳思谋信息科技有限公司 | Video denoising data set generation method and device, computer equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110131460A1 (en) * | 2009-12-02 | 2011-06-02 | Acer Incorporated | Method for repairing image |
CN102231790A (en) * | 2011-06-23 | 2011-11-02 | 上海大学 | Method for restoring scratches of video sequence |
EP2482558A1 (en) * | 2009-11-03 | 2012-08-01 | Huawei Technologies Co., Ltd. | Method, apparatus and system for evaluation of video quality |
CN105809639A (en) * | 2016-03-03 | 2016-07-27 | 上海大学 | Restoration method for color fading and flashing in old films |
CN206249426U (en) * | 2016-09-30 | 2017-06-13 | 宁波市东望智能系统工程有限公司 | A kind of image restoration system |
CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
CN109887515A (en) * | 2019-01-29 | 2019-06-14 | 北京市商汤科技开发有限公司 | Audio-frequency processing method and device, electronic equipment and storage medium |
-
2019
- 2019-07-30 CN CN201910692753.6A patent/CN110378860B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2482558A1 (en) * | 2009-11-03 | 2012-08-01 | Huawei Technologies Co., Ltd. | Method, apparatus and system for evaluation of video quality |
US20110131460A1 (en) * | 2009-12-02 | 2011-06-02 | Acer Incorporated | Method for repairing image |
CN102231790A (en) * | 2011-06-23 | 2011-11-02 | 上海大学 | Method for restoring scratches of video sequence |
CN105809639A (en) * | 2016-03-03 | 2016-07-27 | 上海大学 | Restoration method for color fading and flashing in old films |
CN206249426U (en) * | 2016-09-30 | 2017-06-13 | 宁波市东望智能系统工程有限公司 | A kind of image restoration system |
CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
CN109887515A (en) * | 2019-01-29 | 2019-06-14 | 北京市商汤科技开发有限公司 | Audio-frequency processing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
丁丰;: "数字图像修复技术在缺损照片处理中的应用探讨", 科技创新与应用, no. 32, pages 107 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113507625A (en) * | 2021-06-22 | 2021-10-15 | 西安理工大学 | Self-adaptive video restoration method |
CN114501139A (en) * | 2022-03-31 | 2022-05-13 | 深圳思谋信息科技有限公司 | Video processing method and device, computer equipment and storage medium |
CN115082357A (en) * | 2022-07-20 | 2022-09-20 | 深圳思谋信息科技有限公司 | Video denoising data set generation method and device, computer equipment and storage medium |
CN115082357B (en) * | 2022-07-20 | 2022-11-25 | 深圳思谋信息科技有限公司 | Video denoising data set generation method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110378860B (en) | 2023-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2016206087A1 (en) | Low-illumination image processing method and device | |
CN111275626B (en) | Video deblurring method, device and equipment based on ambiguity | |
CN109743473A (en) | Video image 3 D noise-reduction method, computer installation and computer readable storage medium | |
CN105046658B (en) | A kind of low-light (level) image processing method and device | |
US10817984B2 (en) | Image preprocessing method and device for JPEG compressed file | |
CN110378860A (en) | Method, apparatus, computer equipment and the storage medium of restored video | |
CN109767408B (en) | Image processing method, image processing device, storage medium and computer equipment | |
CN112419162A (en) | Image defogging method and device, electronic equipment and readable storage medium | |
KR102182697B1 (en) | Apparatus and method for processing image | |
CN111445424B (en) | Image processing method, device, equipment and medium for processing mobile terminal video | |
CN111951172A (en) | Image optimization method, device, equipment and storage medium | |
CN107301662A (en) | Compression restoration methods, device, equipment and the storage medium of depth image | |
CN104992419A (en) | Super pixel Gaussian filtering pre-processing method based on JND factor | |
CN113612996A (en) | Video denoising method and device based on time domain filtering | |
US7873226B2 (en) | Image encoding apparatus | |
Liang et al. | Learning to remove sandstorm for image enhancement | |
CN115131229A (en) | Image noise reduction and filtering data processing method and device and computer equipment | |
CN108805873A (en) | Image processing method and device | |
US11501404B2 (en) | Method and system for data processing | |
Lin et al. | Deep multi-scale residual learning-based blocking artifacts reduction for compressed images | |
CN110136085B (en) | Image noise reduction method and device | |
CN114648467B (en) | Image defogging method and device, terminal equipment and computer readable storage medium | |
CN116433525A (en) | Underwater image defogging method based on edge detection function variation model | |
CN115471413A (en) | Image processing method and device, computer readable storage medium and electronic device | |
CN111382772B (en) | Image processing method and device and terminal equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |