Score: 1

Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Published: November 20, 2025 | arXiv ID: 2511.16555v1

By: Junpeng Jing , Weixun Luo , Ye Mao and more

Potential Business Impact:

Makes computers see depth with less power.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
🇬🇧 United Kingdom

Page Count
11 pages

Category
Computer Science:
CV and Pattern Recognition