2019/04/10 by Junhwa Hur, Stefan Roth, Hur, Junhwa +1 · 1 voice · 7 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.1904.05290
To appear in CVPR 2019
arxiv created 2019/04/10 · openalex publication_date 2019/04/10 · arxiv published 2019/04/10 · arxiv updated 2019/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multiple stages or across the levels of a coarse-to-fine representation. While leading to more accurate results, the downside of this is an increased number of parameters. Taking inspiration from both classical energy minimization approaches as well as residual networks, we propose an iterative residual refinement (IRR) scheme based on weight sharing that can be combined with several backbone networks. It reduces the number of parameters, improves the accuracy, or even achieves both. Moreover, we show that integrating occlusion prediction and bi-directional flow estimation into our IRR scheme can further boost the accuracy. Our full network achieves state-of-the-art results for both optical flow and occlusion estimation across several standard datasets.