Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers
Year: 2020
Type: preprint
Abstract: Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence correspondence perspective to replace cost volume construction with dense pixel matching using position information and attention. This approach, named STereo TRansformer (STTR), has several advantages: It 1) relaxes the limitation of a fixed disparity range, 2) identifies occluded regions and provides confidence estimates, and 3) imposes uniqueness constraints during the matching process. We report promising results on both synthetic and real-world datasets and demonstrate that STTR generalizes across different domains, even without fine-tuning.
Source: arXiv (Cornell University)
Authors: Li, Zhaoshuo, Liu, Xingtong, Drenkow, Nathan, Ding, Andy, Creighton, Francis X., Taylor, Russell H., Unberath, Mathias
Institution: Johns Hopkins University
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Johns Hopkins University
OpenAlex ID: W3203576757