高解像度画像に対する階層的ディープステレオマッチング
Hierarchical Deep Stereo Matching on High-resolution Images
粗から細への階層で対応点を段階的に探索するステレオマッチング手法を提案し、高解像度データセットも導入。Middlebury-v3とKITTI-15でSOTAかつ高速、低遅延で近距離の視差予測が可能。
著者: Gengshan Yang, Joshua Manela, Michael Happold, Deva Ramanan
分類: cs.CV, cs.RO
原文アブストラクト
We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-art (SOTA) methods struggle to process high-res imagery because of memory constraints or speed limitations. To address this issue, we propose an end-to-end framework that searches for correspondences incrementally over a coarse-to-fine hierarchy. Because high-res stereo datasets are relatively rare, we introduce a dataset with high-res stereo pairs for both training and evaluation. Our approach achieved SOTA performance on Middlebury-v3 and KITTI-15 while running significantly faster than its competitors. The hierarchical design also naturally allows for anytime on-demand reports of disparity by capping intermediate coarse results, allowing us to accurately predict disparity for near-range structures with low latency (30ms). We demonstrate that the performance-vs-speed trade-off afforded by on-demand hierarchies may address sensing needs for time-critical applications such as autonomous driving.
