paper-with-me

홈 › Papers

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

2015-08-21 · ICCV 2015 12 · Christian Bailer, Bertram Taetz, Didier Stricker

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this paper we present a dense correspondence field approach that is much less outlier prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields. Our approach is conceptually novel as it does not require explicit regularization, smoothing (like median filtering) or a new data term, but solely our novel purely data based search strategy that finds most inliers (even for small objects), while it effectively avoids finding outliers. Moreover, we present novel enhancements for outlier filtering. We show that our approach is better suited for large displacement optical flow estimation than state-of-the-art descriptor matching techniques. We do so by initializing EpicFlow (so far the best method on MPI-Sintel) with our Flow Fields instead of their originally used state-of-the-art descriptor matching technique. We significantly outperform the original EpicFlow on MPI-Sintel, KITTI and Middlebury.

📄 PDF Abstract BibTeX arXiv:1508.05151

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

2017-03-07 · ICCV 2015 · Christian Bailer, Bertram Taetz, Didier Stricker

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being d…

Optical Flow EstimationPatch Matching

Dense Wide-Baseline Scene Flow From Two Handheld Video Cameras

2016-09-16 · Christian Richardt, Hyeongwoo Kim, Levi Valgaerts, Christian Theobalt

We propose a new technique for computing dense scene flow from two handheld videos with wide camera baselines and different photometric properties due to different sensors or camera settings like exposure and white balan…

Vocal Bursts Valence Prediction

DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences

2014-06-01 · CVPR 2014 6 · Hongsheng Yang, Wen-Yan Lin, Jiangbo Lu

Establishing dense correspondences reliably between a pair of images is an important vision task with many applications. Though significant advance has been made towards estimating dense stereo and optical flow fields fo…

Optical Flow Estimation

Learning Probabilistic Coordinate Fields for Robust Correspondences

2023-06-07 · Weiyue Zhao, Hao Lu, Xinyi Ye, Zhiguo Cao 외

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in corr…

Camera Pose EstimationImage RegistrationPose Estimation

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

2018-07-09 · ECCV 2018 9 · Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra…

regressionSemantic correspondence