English

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers

Computer Vision and Pattern Recognition 2021-08-27 v4

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.

Keywords

Cite

@article{arxiv.2011.02910,
  title  = {Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers},
  author = {Zhaoshuo Li and Xingtong Liu and Nathan Drenkow and Andy Ding and Francis X. Creighton and Russell H. Taylor and Mathias Unberath},
  journal= {arXiv preprint arXiv:2011.02910},
  year   = {2021}
}

Comments

Our code is available at https://github.com/mli0603/stereo-transformer

R2 v1 2026-06-23T19:56:29.693Z