Fast Edge-Preserving Patchmatch for Large Displacement Optical Flow

Linchao Bao, Qingxiong Yang*, Hailin Jin

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

94 Citations (Scopus)

Abstract

We present a fast optical flow algorithm that can handle large displacement motions. Our algorithm is inspired by recent successes of local methods in visual correspondence searching as well as approximate nearest neighbor field algorithms. The main novelty is a fast randomized edge-preserving approximate nearest neighbor field algorithm which propagates self-similarity patterns in addition to offsets. Experimental results on public optical flow benchmarks show that our method is significantly faster than state-of-the-art methods without compromising on quality, especially when scenes contain large motions.
Original languageEnglish
Title of host publicationProceedings - 2014 IEEE Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages3534-3541
ISBN (Electronic)9781479951185
ISBN (Print)9781479951178
DOIs
Publication statusPublished - Jun 2014
Event27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014) - Columbus, United States
Duration: 23 Jun 201428 Jun 2014

Publication series

Name
ISSN (Print)1063-6919

Conference

Conference27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)
PlaceUnited States
CityColumbus
Period23/06/1428/06/14

Research Keywords

  • Bilateral Filter
  • Edge-Preserving
  • Large Displacement
  • Motion Estimation
  • Optical Flow
  • PatchMatch

Fingerprint

Dive into the research topics of 'Fast Edge-Preserving Patchmatch for Large Displacement Optical Flow'. Together they form a unique fingerprint.

Cite this