- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Video Completion via Spatio-temporally Consistent Motion Inpainting
-
- Roxas Menandro
- The University of Tokyo
-
- Shiratori Takaaki
- Microsoft Research Asia
-
- Ikeuchi Katsushi
- The University of Tokyo
Description
Given an image sequence with corrupted pixels, usually big holes that span over several frames, we propose to complete the missing parts using an iterative optimization approach which minimizes an optical flow functional and propagates the color information simultaneously. Inside one iteration of the optical flow estimation, we use the solved motion field to propagate the color and then use the newly inpainted color back to the brightness constraint of the optical flow functional. We then introduce a spatially dependent blending factor, called the mask function, to control the effect of the newly propagated color. We also add a trajectory constraint by solving the forward and backward flow simultaneously using three frames. Finally, we minimize the functional by using alternating direction method of multipliers.
Journal
-
- IPSJ Transactions on Computer Vision and Applications
-
IPSJ Transactions on Computer Vision and Applications 6 (0), 98-102, 2014
Information Processing Society of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001205295466496
-
- NII Article ID
- 130004679098
-
- ISSN
- 18826695
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- OpenAIRE
-
- Abstract License Flag
- Disallowed