Skip to Main content Skip to Navigation
New interface
Conference papers

DeepFlow: Large displacement optical flow with deep matching

Philippe Weinzaepfel 1 Jérôme Revaud 1 Zaid Harchaoui 1 Cordelia Schmid 1 
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Optical flow computation is a key component in many computer vision systems designed for tasks such as action detection or activity recognition. However, despite several major advances over the last decade, handling large displacement in optical flow remains an open problem. Inspired by the large displacement optical flow of Brox and Malik, our approach, termed DeepFlow, blends a matching algorithm with a variational approach for optical flow. We propose a descriptor matching algorithm, tailored to the optical flow problem, that allows to boost performance on fast motions. The matching algorithm builds upon a multi-stage architecture with 6 layers, interleaving convolutions and max-pooling, a construction akin to deep convolutional nets. Using dense sampling, it allows to efficiently retrieve quasi-dense correspondences, and enjoys a built-in smoothing effect on descriptors matches, a valuable asset for integration into an energy minimization framework for optical flow estimation. DeepFlow efficiently handles large displacements occurring in realistic videos, and shows competitive performance on optical flow benchmarks. Furthermore, it sets a new state-of-the-art on the MPI-Sintel dataset.
Document type :
Conference papers
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Wednesday, October 16, 2013 - 9:38:57 AM
Last modification on : Thursday, January 20, 2022 - 5:30:16 PM
Long-term archiving on: : Friday, January 17, 2014 - 4:37:27 AM


Files produced by the author(s)




Philippe Weinzaepfel, Jérôme Revaud, Zaid Harchaoui, Cordelia Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. pp.1385-1392, ⟨10.1109/ICCV.2013.175⟩. ⟨hal-00873592⟩



Record views


Files downloads