CN103402098A - Video frame interpolation method based on image interpolation - Google Patents
Video frame interpolation method based on image interpolation Download PDFInfo
- Publication number
- CN103402098A CN103402098A CN2013103617102A CN201310361710A CN103402098A CN 103402098 A CN103402098 A CN 103402098A CN 2013103617102 A CN2013103617102 A CN 2013103617102A CN 201310361710 A CN201310361710 A CN 201310361710A CN 103402098 A CN103402098 A CN 103402098A
- Authority
- CN
- China
- Prior art keywords
- frame
- motion vector
- interpolation
- meet
- piece
- 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
Images
Abstract
The invention discloses a video frame interpolation method based on an image interpolation. A video frame interpolation scheme based on image inpainting is designed to solve the problems that bi-directional block search cannot obtain a good motion estimation result, and unidirectional block search can generate overlapping and cavity problems in an interpolation frame of interpolation compensation. The method comprises the steps that unidirectional motion estimation with a size of a three-level variable block and motion vector field smoothing filtering are performed between adjacent frames; an initial interpolation frame is obtained by the interpolation compensation, cavity and overlapping areas in the initial interpolation frame are marked; a to-be-inpainted area mask is generated; and finally, the image inpainting is performed on the initial interpolation frame according to the mask, and a final interpolation frame is obtained. The method can effectively reduce a blocking effect in the interpolation frame and improve the image quality, is easy to realize and high in processing efficiency, and is suitable for real-time frame rate upconversion of a high definition video.
Description
Technical field
The invention belongs to Video processing and transmission field, be specifically related to a kind of interleave of video based on image interpolation method.
Background technology
Along with the development of digital TV in high resolution (HDTV) and high-end multimedia information system, people are more and more higher to the visual effect requirement of video source, therefore need to improve the frame per second of existing video program source to reach better visual effect; Meanwhile, although the encoding and decoding technique in transmission of video can obtain very high compression ratio at present, yet, in order to adapt to the restriction of some network bandwidths, usually the spatial and temporal resolution of vision signal is reduced and makes data volume still less, can realize by the coding side frame-skipping in time domain.Like this, in the low frame-rate video of decoding end, will inevitably cause that motion is discontinuous, the degeneration of picture quality, especially more obvious in rapid movement and complex scene.For this reason, can adopt the video interleave in decoding end, namely on frame per second, switch technology is recovered original frame per second to improve the subjective vision effect of video image, and this technology also can be used for the conversion between different frame per second video formats.
The video interleave is conversion (Frame Rate Up-Conversion, FRUC) technology on frame per second, and it, by insert the mode of intermediate frame between the decoding end consecutive frame, promotes paramount frame per second with video from low frame per second, realizes the conversion between different frame per second.Along with people's improving constantly the video effect requirement, need larger video resolution (and display size), frame per second faster, these demands make the requirement of the speed of processing module and storage space more and more higher, have brought challenge for the real-time processing of video frequency doubling system.
Because simple frame repeats, frame on average can produce motion jitter and fuzzy, therefore the method that conversion is adopted usually on frame per second in actual applications is based on motion compensated interpolation (the Motion-Compensated Interpolation of piece coupling, MCI), the interpolation frame quality that obtains of the method depends on the precision of estimation of motion vectors.
But, traditional piece coupling is front and back two frames " unidirectional " search while carrying out estimation, and in the middle of making, a pixel of interpolation frame may have a plurality of movement locus to pass through, and does not perhaps have movement locus to pass through, and produce respectively " overlapping " and " cavity " problem, ask for an interview Fig. 1.
This technical problem obtains certain solution because of " bi-directional motion estimation " technology, " bi-directional motion estimation " is to use piece in interpolation frame as positioning datum, search for symmetrically match block in the frame of front and back, pixel " overlapping " and " cavity " that just can not exist the one-way movement method of estimation to bring like this when the Interpolation compensation intermediate frame; However, " bi-directional motion estimation " often can not obtain motion vector accurately, make the compensation interpolation after interpolation frame blocking effect appears.
Can effectively improve the blocking effect that reduces in interpolation frame, the video interpolation technique that improves picture quality, be the research emphasis of this area always.
Summary of the invention
For the problems referred to above, the present invention proposes a kind ofly can effectively improve the blocking effect that reduces in interpolation frame, the interpolation method of the video based on image interpolation that improves picture quality.
The technical solution adopted in the present invention is: a kind of interleave of video based on image interpolation method, it is characterized in that, and comprise the following steps:
Step 1:, for present frame,, take the former frame in adjacent two frames as reference frame, by the unidirectional initial motion of 16 * 16 block search, estimate, obtain the initial motion vectors of present frame;
Step 2: the initial motion vectors to described present frame is carried out the disposal of gentle filter, obtains first motion vector field;
Does step 3: judgement: the piece that described initial motion is estimated meet piece match search criterion?
If meet, at first use 8 * 8 directly to inherit these motion vectors, then use 4 * 4 directly to inherit these motion vectors, described step 8 is carried out in last redirect;
If do not meet, the piece that will not meet piece match search criterion splits, and carries out the secondary estimation, obtains the motion vector of estimating for the second time of these pieces;
Step 4: the described motion vector of estimating is for the second time carried out the disposal of gentle filter, obtain second level motion vector field;
Does step 5: judgement: the piece of described secondary estimation meet piece match search criterion?
, if meet, use 4 * 4 directly to inherit these motion vectors, and described step 8 is carried out in redirect;
If do not meet, the piece that will not meet piece match search criterion continues to split, and carries out three grades of estimation, obtains the motion vector of estimating for the third time of these pieces;
Step 6: the described motion vector of estimating is for the third time carried out the disposal of gentle filter, obtain third level motion vector field;
Does step 7: judgement: the piece of described three grades of estimation meet piece match search criterion?
, if meet, with described third level motion vector field, be final motion vector field, and described step 8 is carried out in redirect;
If do not meet, to estimate unsuccessfully, its motion vector directly distributes according to the block motion vector around it;
Step 8: according to described final motion vector field, present frame is carried out Interpolation compensation, obtain initial interpolation frame, and the pixel in " cavity " and " overlapping " zone is carried out mark, obtain waiting to repair regional mask;
Step 9: wait to repair regional mask initial interpolation frame is carried out image mending according to described, obtain final interpolation frame.
As preferably, described in step 1 based on block search, employing be the three-dimensional recursive search algorithm.
As preferably, the secondary estimation described in step 3, being 8 * 8 and inheriting the results that initial motion is estimated of employing, to the piece in previous step estimation again.
As preferably, three grades of estimation described in step 5, employing be 4 * 4 results of inheriting the secondary estimation, to the piece in previous step estimation again.
As preferably, described the disposal of gentle filter, employing be that 3 * 3 window carries out medium filtering and processes.
As preferably, described in step 9, initial interpolation frame is carried out image mending, employing be fast marching algorithms.
With respect to prior art, the present invention can effectively improve the blocking effect that reduces in interpolation frame, improve picture quality, is easy to realize, treatment effeciency is high, is applicable to change on the real time frame rate of HD video.
Description of drawings
Fig. 1: " cavity " and " overlapping " schematic diagram that Interpolation compensation produces is estimated in the one-way movement of prior art of the present invention.
Fig. 2: the algorithm flow chart of the specific embodiment of the invention.
Fig. 3: the 3-D RS spatio-temporal prediction candidate vector position view of the specific embodiment of the invention.
Fig. 4: three grades of estimation piecemeal schematic diagrames of the specific embodiment of the invention.
Fig. 5: mask figure is repaired in the cavity of the specific embodiment of the invention, overlapping region.
Embodiment
The present invention is further elaborated below with reference to the drawings and specific embodiments.
Ask for an interview Fig. 2, the technical solution adopted in the present invention is: a kind of interleave of video based on image interpolation method comprises the following steps:
Step 1:, for present frame, use former frame in adjacent two frames as the reference frame, utilize three-dimensional recursive search (3-D Recursive Search, 3-D RS) algorithm, carry out one-way movement with 16 * 16 and estimate, obtain the initial motion vectors of present frame.
Step 2: the initial motion vectors of present frame is carried out medium filtering process, obtain first motion vector field, and the piece greater than absolute error and threshold values (threshold_SAD) is carried out mark.
Does step 3: judgement: the piece that initial motion is estimated meet piece match search criterion?
If meet, at first use 8 * 8 directly to inherit these motion vectors, then use 4 * 4 directly to inherit these motion vectors, last redirect execution step 8;
If do not meet, the piece that will not meet piece match search criterion splits, and carries out the secondary estimation, obtains the motion vector of estimating for the second time of these pieces.
Step 4: the motion vector of estimating is for the second time carried out medium filtering process, obtain second level motion vector field, and to the mark again of the piece greater than 1/4th absolute errors and threshold values (threshold_SAD/4).
Does step 5: judgement: the piece of secondary estimation meet piece match search criterion?
If meet, use 4 * 4 directly to inherit these motion vectors, and redirect execution step 8;
If do not meet, the piece that will not meet piece match search criterion continues to split, and carries out three grades of estimation, obtains the motion vector of estimating for the third time of these pieces;
Step 6: the motion vector of estimating is for the third time carried out medium filtering process, obtain third level motion vector field, and to the mark again of the piece greater than ten sixth absolute errors and threshold values (threshold_SAD/16).
Does step 7: judgement: the piece of three grades of estimation meet piece match search criterion?
If meet, with third level motion vector field, be final motion vector field, and redirect execution step 8;
If do not meet, to estimate unsuccessfully, its block motion vector greater than ten sixth absolute errors and threshold values (threshold_SAD/16) is directly distributed by the result of the block motion vector medium filtering around it.
Step 8: according to final motion vector field, present frame is carried out Interpolation compensation, obtain initial interpolation frame, and the pixel in " cavity " and " overlapping " zone is carried out mark, obtain waiting to repair regional mask.
Step 9: utilize the image mending algorithm of advancing fast, according to waiting that repairing regional mask repairs initial interpolation frame, obtains final interpolation frame.
The present invention is written to interpolation frame between original two frames, realizes changing on video frame rate 2 frequencys multiplication.
Existing a lot of ripe block matching algorithms in the coding and decoding video field.But, require movable information can reflect the real motion of object in the application of video interleave, the motion vector that only depends on matching error to determine is likely completely different with real motion, makes the interpolation frame of motion compensation produce the image information that is not inconsistent with subjective vision.Because the motion of object video has continuity, so also there is temporal correlation between motion vector.
Ask for an interview Fig. 3, three-dimensional recursive search (3-D Recursive Search based on the piece coupling of the present invention, 3-D RS) be the searching algorithm that utilizes the prediction of sports ground temporal correlation, can not only obtain more level and smooth motion vector field, also reduced computing cost simultaneously.If F (x, t) is the brightness of pixel x in the t frame, T is the frame number interval, and B (X) represents the piece in reference frame, X is the position of piece, and C is candidate vector, U (X, t) for upgrading vector, α is constant, and in 3-D RS algorithm, motion estimation error criterion calculating formula is:
Wherein, candidate vector C is the element in the motion vector set of room and time adjacent block of current block.Because the motion vector of current block and its time, space adjacent block motion vector are close, but not identical, if all candidate vectors do not meet actual conditions all from the original value of adjacent block motion vector.Therefore, add that is upgraded a vector for the original motion vector, the candidate motion vector that obtains will more approaching reality, more accurate.
Ask for an interview Fig. 4, when a piece comprises a plurality of different motion object,, particularly at movement edge, can't obtain the estimated vector of correct Describing Motion.Therefore the present invention adopts multistage coupling, the search of " from coarse to fine ", and the motion vector of upper level can propagate into next stage, and the estimated value of next stage is the further refinement to the upper level estimated result.The present invention adopts three grades of estimation, after the estimation of every one-level, vector field is carried out medium filtering with 3 * 3 window, obtains more level and smooth motion vector field, then uses
Carry out Interpolation compensation, wherein s is the pixel in interpolation frame, and v is motion vector.
Ask for an interview Fig. 5, in initial interpolation frame, " cavity " and " overlapping " zone is carried out mark and is generated mask; Finally, the present invention introduces these pixels of image mending technology completion.Owing to only need fill up some narrow and small zones after interpolation, the present invention adopts fast marching algorithms (Fast marching method, FMM), and processing speed is fast.
These are only preferred embodiment of the present invention, not be used for limiting protection scope of the present invention, therefore, all any modifications of doing within the spirit and principles in the present invention, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (6)
1. the interleave of the video based on an image interpolation method, is characterized in that, comprises the following steps:
Step 1:, for present frame,, take the former frame in adjacent two frames as reference frame, by the unidirectional initial motion of 16 * 16 block search, estimate, obtain the initial motion vectors of present frame;
Step 2: the initial motion vectors to described present frame is carried out the disposal of gentle filter, obtains first motion vector field;
Does step 3: judgement: the piece that described initial motion is estimated meet piece match search criterion?
If meet, at first use 8 * 8 directly to inherit these motion vectors, then use 4 * 4 directly to inherit these motion vectors, described step 8 is carried out in last redirect;
If do not meet, the piece that will not meet piece match search criterion splits, and carries out the secondary estimation, obtains the motion vector of estimating for the second time of these pieces;
Step 4: the described motion vector of estimating is for the second time carried out the disposal of gentle filter, obtain second level motion vector field;
Does step 5: judgement: the piece of described secondary estimation meet piece match search criterion?
, if meet, use 4 * 4 directly to inherit these motion vectors, and described step 8 is carried out in redirect;
If do not meet, the piece that will not meet piece match search criterion continues to split, and carries out three grades of estimation, obtains the motion vector of estimating for the third time of these pieces;
Step 6: the described motion vector of estimating is for the third time carried out the disposal of gentle filter, obtain third level motion vector field;
Does step 7: judgement: the piece of described three grades of estimation meet piece match search criterion?
, if meet, with described third level motion vector field, be final motion vector field, and described step 8 is carried out in redirect;
If do not meet, to estimate unsuccessfully, its motion vector directly distributes according to the block motion vector around it;
Step 8: according to described final motion vector field, present frame is carried out Interpolation compensation, obtain initial interpolation frame, and the pixel in " cavity " and " overlapping " zone is carried out mark, obtain waiting to repair regional mask;
Step 9: wait to repair regional mask initial interpolation frame is carried out image mending according to described, obtain final interpolation frame.
2. the interleave of the video based on image interpolation method according to claim 1 is characterized in that: described in step 1 based on block search, employing be the three-dimensional recursive search algorithm.
3. the interleave of the video based on image interpolation method according to claim 1 is characterized in that: the secondary estimation described in step 3, being 8 * 8 and inheriting the results that initial motion is estimated of employing, to the piece in previous step estimation again.
4. the interleave of the video based on image interpolation method according to claim 1 is characterized in that: three grades of estimation described in step 5, employing be 4 * 4 results of inheriting the secondary estimation, to the piece in previous step estimation again.
5. the interleave of the video based on image interpolation method according to claim 1 is characterized in that: described the disposal of gentle filter, employing be that 3 * 3 window carries out medium filtering and processes.
6. the interleave of the video based on image interpolation method according to claim 1 is characterized in that: described in step 9, initial interpolation frame is carried out image mending, employing be fast marching algorithms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310361710.2A CN103402098B (en) | 2013-08-19 | 2013-08-19 | A kind of video frame interpolation method based on image interpolation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310361710.2A CN103402098B (en) | 2013-08-19 | 2013-08-19 | A kind of video frame interpolation method based on image interpolation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103402098A true CN103402098A (en) | 2013-11-20 |
| CN103402098B CN103402098B (en) | 2016-07-06 |
Family
ID=49565610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310361710.2A Expired - Fee Related CN103402098B (en) | 2013-08-19 | 2013-08-19 | A kind of video frame interpolation method based on image interpolation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103402098B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105517671A (en) * | 2015-05-25 | 2016-04-20 | 北京大学深圳研究生院 | Video frame interpolation method and system based on optical flow method |
| CN106331723A (en) * | 2016-08-18 | 2017-01-11 | 上海交通大学 | Video frame rate up-conversion method and system based on motion region segmentation |
| CN107172426A (en) * | 2017-06-23 | 2017-09-15 | 西安电子科技大学 | Conversion method in the parallel frame per second of OpenCL based on double MIC |
| CN107396111A (en) * | 2017-07-13 | 2017-11-24 | 河北中科恒运软件科技股份有限公司 | The compensation method of automatic video frequency interleave and system in mediation reality |
| CN107657591A (en) * | 2017-09-05 | 2018-02-02 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN110163892A (en) * | 2019-05-07 | 2019-08-23 | 国网江西省电力有限公司检修分公司 | Learning rate Renewal step by step method and dynamic modeling system based on estimation interpolation |
| CN110896492A (en) * | 2018-09-13 | 2020-03-20 | 传线网络科技（上海）有限公司 | Image processing method, device and storage medium |
| CN111491204A (en) * | 2020-04-17 | 2020-08-04 | Oppo广东移动通信有限公司 | Video repair method, video repair device, electronic equipment and computer-readable storage medium |
| CN111586321A (en) * | 2020-05-08 | 2020-08-25 | Oppo广东移动通信有限公司 | Video generation method and device, electronic equipment and computer-readable storage medium |
| CN111741304A (en) * | 2019-03-25 | 2020-10-02 | 四川大学 | Method for combining frame rate up-conversion and HEVC (high efficiency video coding) based on motion vector refinement |
| CN113673588A (en) * | 2021-08-12 | 2021-11-19 | 连尚(北京)网络科技有限公司 | Method, apparatus, medium, and program product for video classification |
| CN114372936A (en) * | 2022-01-10 | 2022-04-19 | 中国人民解放军国防科技大学 | Infrared dim target detection method based on image inpainting technology |
| CN114554248A (en) * | 2022-04-27 | 2022-05-27 | 杭州微帧信息科技有限公司 | Video frame interpolation method based on neural network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103209334A (en) * | 2013-03-18 | 2013-07-17 | 中山大学 | Virtual viewpoint synthesis and void repairing method for 2.5D videos to multi-view (three-dimensional) 3D videos |
-
2013
- 2013-08-19 CN CN201310361710.2A patent/CN103402098B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103209334A (en) * | 2013-03-18 | 2013-07-17 | 中山大学 | Virtual viewpoint synthesis and void repairing method for 2.5D videos to multi-view (three-dimensional) 3D videos |
Non-Patent Citations (3)
| Title |
|---|
| 侯正信: "帧率提升中的三维递归搜索块匹配改进算法", 《计算机工程与应用》 * |
| 肖志云: "基于小波变换的图像修复算法", 《内蒙古工业大学学报》 * |
| 贾茜: "基于三维递归搜索的多级运动估计视频帧率上转换算法", 《电子与信息学报》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016187776A1 (en) * | 2015-05-25 | 2016-12-01 | 北京大学深圳研究生院 | Video frame interpolation method and system based on optical flow method |
| CN105517671A (en) * | 2015-05-25 | 2016-04-20 | 北京大学深圳研究生院 | Video frame interpolation method and system based on optical flow method |
| CN106331723A (en) * | 2016-08-18 | 2017-01-11 | 上海交通大学 | Video frame rate up-conversion method and system based on motion region segmentation |
| CN107172426B (en) * | 2017-06-23 | 2019-10-11 | 西安电子科技大学 | Conversion method in the parallel frame per second of OpenCL based on double MIC |
| CN107172426A (en) * | 2017-06-23 | 2017-09-15 | 西安电子科技大学 | Conversion method in the parallel frame per second of OpenCL based on double MIC |
| CN107396111B (en) * | 2017-07-13 | 2020-07-14 | 河北中科恒运软件科技股份有限公司 | Automatic video frame interpolation compensation method and system in mediated reality |
| CN107396111A (en) * | 2017-07-13 | 2017-11-24 | 河北中科恒运软件科技股份有限公司 | The compensation method of automatic video frequency interleave and system in mediation reality |
| CN107657591A (en) * | 2017-09-05 | 2018-02-02 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN110896492A (en) * | 2018-09-13 | 2020-03-20 | 传线网络科技（上海）有限公司 | Image processing method, device and storage medium |
| CN110896492B (en) * | 2018-09-13 | 2022-01-28 | 阿里巴巴（中国）有限公司 | Image processing method, device and storage medium |
| CN111741304A (en) * | 2019-03-25 | 2020-10-02 | 四川大学 | Method for combining frame rate up-conversion and HEVC (high efficiency video coding) based on motion vector refinement |
| CN110163892A (en) * | 2019-05-07 | 2019-08-23 | 国网江西省电力有限公司检修分公司 | Learning rate Renewal step by step method and dynamic modeling system based on estimation interpolation |
| CN110163892B (en) * | 2019-05-07 | 2023-06-20 | 国网江西省电力有限公司检修分公司 | Learning rate progressive updating method based on motion estimation interpolation and dynamic modeling system |
| CN111491204A (en) * | 2020-04-17 | 2020-08-04 | Oppo广东移动通信有限公司 | Video repair method, video repair device, electronic equipment and computer-readable storage medium |
| CN111491204B (en) * | 2020-04-17 | 2022-07-12 | Oppo广东移动通信有限公司 | Video repair method, video repair device, electronic equipment and computer-readable storage medium |
| CN111586321B (en) * | 2020-05-08 | 2023-05-12 | Oppo广东移动通信有限公司 | Video generation method, device, electronic equipment and computer readable storage medium |
| CN111586321A (en) * | 2020-05-08 | 2020-08-25 | Oppo广东移动通信有限公司 | Video generation method and device, electronic equipment and computer-readable storage medium |
| CN113673588A (en) * | 2021-08-12 | 2021-11-19 | 连尚(北京)网络科技有限公司 | Method, apparatus, medium, and program product for video classification |
| CN114372936A (en) * | 2022-01-10 | 2022-04-19 | 中国人民解放军国防科技大学 | Infrared dim target detection method based on image inpainting technology |
| CN114554248A (en) * | 2022-04-27 | 2022-05-27 | 杭州微帧信息科技有限公司 | Video frame interpolation method based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103402098B (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103402098A (en) | Video frame interpolation method based on image interpolation | |
| Wang et al. | Frame rate up-conversion using trilateral filtering | |
| CN106210767B (en) | Video frame rate up-conversion method and system for intelligently improving motion fluency | |
| Kang et al. | Motion compensated frame rate up-conversion using extended bilateral motion estimation | |
| Dikbas et al. | Novel true-motion estimation algorithm and its application to motion-compensated temporal frame interpolation | |
| CN105517671B (en) | Video frame interpolation method and system based on optical flow method | |
| US7440008B2 (en) | Video stabilization method | |
| CN103888767B (en) | A kind of frame per second method for improving that UMH block-based motion estimations are combined with optical flow field estimation | |
| CN102123283B (en) | Interpolated frame acquisition method and device in video frame rate conversion | |
| CN103220488A (en) | Up-conversion device and method of video frame rate | |
| CN101207707A (en) | System and method for advancing frame frequency based on motion compensation | |
| Lee et al. | Frame rate up conversion based on variational image fusion | |
| CN107483960B (en) | Motion compensation frame rate up-conversion method based on spatial prediction | |
| CN108574844B (en) | Multi-strategy video frame rate improving method for space-time significant perception | |
| WO2014161280A1 (en) | Multi-level bidirectional motion estimation method and device | |
| CN113850718A (en) | Video synchronization space-time super-resolution method based on inter-frame feature alignment | |
| CN103152566B (en) | A kind of video frame rate method for improving | |
| Choi et al. | Triple-frame-based bi-directional motion estimation for motion-compensated frame interpolation | |
| Huang et al. | Algorithm and architecture design of multirate frame rate up-conversion for ultra-HD LCD systems | |
| CN103313059B (en) | The decision method of occlusion areas during a kind of frame per second promotes | |
| Han et al. | Frame rate up-conversion for high-definition video applications | |
| Lee et al. | High frame rate motion compensated frame interpolation in high-definition video processing | |
| CN104580978A (en) | Video detecting and processing method and video detecting and processing device | |
| CN101600105A (en) | Frame frequency lifting method | |
| Li et al. | Motion-compensated frame interpolation using patch-based sparseland model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160706 Termination date: 20180819 |