Optical Flow in Mostly Rigid Scenes

Jonas Wulff, Laura Sevilla-Lara, Michael J. Black

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static world or optical flow for general unconstrained scenes. We combine these approaches in an optical flow algorithm that estimates an explicit segmentation of moving objects from appearance and physical constraints. In static regions we take advantage of strong constraints to jointly estimate the camera motion and the 3D structure of the scene over multiple frames. This allows us to also regularize the structure instead of the motion. Our formulation uses a Plane+Parallax framework, which works even under small baselines, and reduces the motion estimation to a one-dimensional search problem, resulting in more accurate estimation. In moving regions the flow is treated as unconstrained, and computed with an existing optical flow method. The resulting Mostly-Rigid Flow (MR-Flow) method achieves state-of-the-art results on both the MPI-Sintel and KITTI-2015 benchmarks.
Original languageEnglish
Title of host publication2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages6911-6920
Number of pages10
ISBN (Electronic)978-1-5386-0457-1
ISBN (Print)978-1-5386-0458-8
DOIs
Publication statusPublished - 9 Nov 2017
Event2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops - Honolulu, United States
Duration: 21 Jul 201726 Jul 2017
http://cvpr2017.thecvf.com/

Publication series

NameIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
ISSN (Print)1063-6919

Conference

Conference2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops
Abbreviated titleCVPR 2017
Country/TerritoryUnited States
CityHonolulu
Period21/07/1726/07/17
Internet address

Keywords

  • cameras
  • image segmentation
  • image sequences
  • motion estimation
  • object detection
  • search problems
  • Mostly-Rigid Flow method
  • MR-Flow
  • rigid scenes
  • natural scenes
  • purely static world
  • general unconstrained scenes
  • optical flow algorithm
  • appearance
  • physical constraints
  • optical flow method
  • camera motion estimation
  • observer motion
  • independent object motion
  • motion recovery
  • moving object explicit segmentation
  • 3D scene structure
  • Plane+Parallax framework
  • one-dimensional search problem
  • MPI-Sintel benchmark
  • KITTI-2015 benchmarks
  • Optical imaging
  • Cameras
  • Motion segmentation
  • Benchmark testing
  • Semantics
  • Estimation
  • Three-dimensional displays

Fingerprint

Dive into the research topics of 'Optical Flow in Mostly Rigid Scenes'. Together they form a unique fingerprint.

Cite this