{"ID":2839173,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16555","arxiv_id":"2511.16555","title":"Lite Any Stereo: Efficient Zero-Shot Stereo Matching","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.","short_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 framewo...","url_abs":"https://arxiv.org/abs/2511.16555","url_pdf":"https://arxiv.org/pdf/2511.16555v3","authors":"[\"Junpeng Jing\",\"Weixun Luo\",\"Ye Mao\",\"Krystian Mikolajczyk\"]","published":"2025-11-20T17:07:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}