English

Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Computer Vision and Pattern Recognition 2026-04-16 v3

Abstract

Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as incapable of zero-shot ability due to their limited capacity. In this paper, we introduce Lite Any Stereo, a stereo depth estimation framework that achieves strong zero-shot generalization while remaining highly efficient. To this end, we design a compact yet expressive backbone to ensure scalability, along with a carefully crafted hybrid cost aggregation module. We further propose a three-stage training strategy on million-scale data to effectively bridge the sim-to-real gap. Together, these components demonstrate that an ultra-light model can deliver strong generalization, ranking 1st across four widely used real-world benchmarks. Remarkably, our model attains accuracy comparable to or exceeding state-of-the-art non-prior-based accurate methods while requiring less than 1% computational cost, setting a new standard for efficient stereo matching.

Keywords

Cite

@article{arxiv.2511.16555,
  title  = {Lite Any Stereo: Efficient Zero-Shot Stereo Matching},
  author = {Junpeng Jing and Weixun Luo and Ye Mao and Krystian Mikolajczyk},
  journal= {arXiv preprint arXiv:2511.16555},
  year   = {2026}
}

Comments

CVPR 2026

R2 v1 2026-07-01T07:47:39.632Z