Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Optical Flow EstimationSimilar Papers 제목 키워드 기반
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
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 MatchingDense Wide-Baseline Scene Flow From Two Handheld Video Cameras
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 PredictionDAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
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 EstimationLearning Probabilistic Coordinate Fields for Robust Correspondences
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 EstimationPARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
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