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

Abstract : 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 to 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [90 references]  Display  Hide  Download

https://hal.inria.fr/hal-01001758
Contributor : Denis Fortun <>
Submitted on : Tuesday, December 22, 2015 - 3:19:43 PM
Last modification on : Wednesday, April 11, 2018 - 1:50:52 AM
Long-term archiving on : Sunday, April 30, 2017 - 12:06:27 AM

File

CVIU_aggreg_revision.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Denis Fortun, Patrick Bouthemy, Charles Kervrann. Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow. Computer Vision and Image Understanding, Elsevier, 2016, pp.17. ⟨10.1016/j.cviu.2015.11.020⟩. ⟨hal-01001758v2⟩

Share

Metrics

Record views

243

Files downloads

241