Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Lite Any Stereo: Efficient Zero-Shot Stereo Matching

About

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.

Junpeng Jing, Weixun Luo, Ye Mao, Krystian Mikolajczyk• 2025

Related benchmarks

TaskDatasetResultRank
Stereo MatchingKITTI 2015 (test)
D1 Error (Overall)1.71
205
Stereo MatchingKITTI 2012 (test)
Outlier Rate (3px, Noc)1.09
89
Stereo MatchingMiddlebury half resolution (test)
Threshold Error Rate7.51
36
Stereo MatchingETH3D full-res (test)
Bad 1.0 Error3.53
17
Stereo MatchingDrivingStereo weather--
9
Showing 5 of 5 rows

Other info

Follow for update