Work

DeepFlow: Large Displacement Optical Flow with Deep Matching

Year: 2013

Type: conference-paper

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 Deep Flow, 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. Deep Flow 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.

Source: IEEE/CVF International Conference on Computer Vision (ICCV)

DOI: 10.1109/iccv.2013.175

Authors: Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid

Institutions: Institut national de recherche en sciences et technologies du numérique, Laboratoire Jean Kuntzmann

Language: English

Topic: Advanced Vision and Imaging

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique