Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
Code (1)
Tasks
Motion SegmentationOptical Flow EstimationScene Flow EstimationSegmentationSimilar Papers 제목 키워드 기반
UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation
Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Ac…
Motion EstimationOptical Flow EstimationPushing the Boundaries of View Extrapolation with Multiplane Images
We explore the problem of view synthesis from a narrow baseline pair of images, and focus on generating high-quality view extrapolations with plausible disocclusions. Our method builds upon prior work in predicting a mul…
MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images
We introduce a method to convert stereo 360{\deg} (omnidirectional stereo) imagery into a layered, multi-sphere image representation for six degree-of-freedom (6DoF) rendering. Stereo 360{\deg} imagery can be captured fr…
GPULevel Set Stereo for Cooperative Grouping with Occlusion
Localizing stereo boundaries is difficult because matching cues are absent in the occluded regions that are adjacent to them. We introduce an energy and level-set optimizer that improves boundaries by encoding the essent…
Occlusion HandlingDepth-Based Selective Blurring in Stereo Images Using Accelerated Framework
We propose a hybrid method for stereo disparity estimation by combining block and region-based stereo matching approaches. It generates dense depth maps from disparity measurements of only 18 % image pixels (left or righ…
CPUDisparity EstimationGPUStereo Disparity Estimation+1