Sparse Aggregation Framework for Optical Flow Estimation

Abstract : We propose a sparse aggregation framework for optical flow estimation to overcome the limitations of variational methods introduced by coarse-to-fine strategies. The idea is to compute parametric motion candidates estimated in overlapping square windows of variable size taken in the semi-local neighborhood of a given point. In the second step, a sparse representation and an optimization procedure in the continuous setting are proposed to compute a motion vector close to motion candidates for each pixel. We demonstrate the feasibility and performance of our two-step approach on image pairs and compare its performances with competitive methods on the Middlebury benchmark.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01138012
Contributor : Denis Fortun <>
Submitted on : Tuesday, March 31, 2015 - 9:11:22 PM
Last modification on : Wednesday, April 11, 2018 - 1:52:32 AM
Long-term archiving on : Tuesday, April 18, 2017 - 6:30:53 AM

File

sparse_aggreg.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01138012, version 1

Collections

Citation

Denis Fortun, Patrick Bouthemy, Charles Kervrann. Sparse Aggregation Framework for Optical Flow Estimation. Scale Space and Variational Methods in Computer Vision, May 2015, Lège Cap Ferret, France. ⟨hal-01138012⟩

Share

Metrics

Record views

182

Files downloads

259