2021/08/12 by Antyanta Bangunharcana, Bangunharcana, Antyanta, Jae Won Cho +10 · 13 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG) #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2108.05773
To appear at IROS 2021. Code is available at https://github.com/antabangun/coex
arxiv created 2021/08/12 · openalex publication_date 2021/08/12 · arxiv updated 2021/08/13 · openalex created_date 2022/09/14 · openalex updated_date 2026/07/28
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume aggregation complements 3D convolutions. However, existing methods with spatially varying operations are complex, cost considerable computation time, and cause memory consumption to increase. In this work, we construct Guided Cost volume Excitation (GCE) and show that simple channel excitation of cost volume guided by image can improve performance considerably. Moreover, we propose a novel method of using top-k selection prior to soft-argmin disparity regression for computing the final disparity estimate. Combining our novel contributions, we present an end-to-end network that we call Correlate-and-Excite (CoEx). Extensive experiments of our model on the SceneFlow, KITTI 2012, and KITTI 2015 datasets demonstrate the effectiveness and efficiency of our model and show that our model outperforms other speed-based algorithms while also being competitive to other state-of-the-art algorithms. Codes will be made available at https://github.com/antabangun/coex.