Multiscale NeighborhoodWise Decision Fusion for Redundancy Detection in Image Pairs

Kervrann, Charles; Boulanger, Jérôme; Pécot, Thierry; Pérez, Patrick; Salamero, Jean

doi:10.1137/100791786

Cited by 2 publications

(2 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A graph-cut optimization scheme has been proposed in [80]. These two formulations (20) and (21) can be found in numerous other works [137,175,213,244]. Similarly, layered approaches [9,223,231,234,257,277] aim at decomposing the observed scene into overlapping layers and introduce information about depth ordering of regions.…”

Section: Segmented Regionsmentioning

confidence: 99%

Optical flow modeling and computation: A survey

Fortun

Bouthémy

Kervrann

2015

Computer Vision and Image Understanding

Self Cite

338

182

View full text Add to dashboard Cite

a b s t r a c tOptical flow estimation is one of the oldest and still most active research domains in computer vision. In 35 years, many methodological concepts have been introduced and have progressively improved performances, while opening the way to new challenges. In the last decade, the growing interest in evaluation benchmarks has stimulated a great amount of work. In this paper, we propose a survey of optical flow estimation classifying the main principles elaborated during this evolution, with a particular concern given to recent developments. It is conceived as a tutorial organizing in a comprehensive framework current approaches and practices. We give insights on the motivations, interests and limitations of modeling and optimization techniques, and we highlight similarities between methods to allow for a clear understanding of their behavior.

show abstract

Section: Segmented Regionsmentioning

confidence: 99%

Optical flow modeling and computation: A survey

Fortun

Bouthémy

Kervrann

2015

Computer Vision and Image Understanding

Self Cite

338

182

View full text Add to dashboard Cite

show abstract

“…Our procedure is simple and exploits the patch distribution 4.691 0.386 MDP-Flow2 [64] 4.006 0.223 P S,α and the correspondences used for motion candidates estimation. Nevertheless, from a more general point of view, the coarse occlusion confidence map could be designed differently, e.g., in the framework of [35].…”

Section: Occlusion Confidence Mapmentioning

confidence: 99%

Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

Fortun

Bouthémy

Kervrann

2016

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.

show abstract

Multiscale NeighborhoodWise Decision Fusion for Redundancy Detection in Image Pairs

Cited by 2 publications

References 103 publications

Optical flow modeling and computation: A survey

Optical flow modeling and computation: A survey

Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

Contact Info

Product

Resources

About