Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow
Authors:
- Linchao BaoLBLinchao Bao
- Qingxiong YangQYQingxiong Yang
- Hailin JinHJHailin Jin
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3534-3541
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.Keywords
This publication has 25 references indexed in Scilit:
- Locally Affine Sparse-to-Dense Matching for Motion and Occlusion Estimation2013
- Constant Time Weighted Median Filtering for Stereo Matching and Beyond2013
- A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind ThemInternational Journal of Computer Vision, 2013
- A Fully-Connected Layered Model of Foreground and Background Flow2013
- Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation2013
- On building an accurate stereo matching system on graphics hardware2011
- Coherency Sensitive Hashing2011
- Fast cost-volume filtering for visual correspondence and beyond2011
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- Determining optical flowArtificial Intelligence, 1981