Lite Any Stereo: Efficient Zero-Shot Stereo Matching

arXiv:2511.16555v3 Announce Type: replace 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.

Related

• On Efficient Variants of Segment Anything Model: A Survey
• Quantization Robustness to Input Degradations for Object Detection
• Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection
• Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials

Source: arXiv cs.CV | 2026-04-16