Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right image to infer depth. Rather than matching individual pixels, 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 of estimation, 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 well across different domains, even without fine-tuning. Our code is publicly available at https://github.com/mli0603/stereo-transformer.

本文介绍了一种名为 STereo TRansformer (STTR) 的方法，采用序列到序列的对应关系角度来进行立体深度估计，使用位置信息和注意力机制来进行密集像素匹配，克服了固定视差范围的限制，识别遮挡区域和提供置信度估计，并在合成和真实数据集上取得了良好的结果。

使用Transformer 从序列到序列视角重新思考立体深度估计