Lite Any Stereo：高效零样本立体匹配
Lite Any Stereo: Efficient Zero-Shot Stereo Matching
提供了一套可复用的轻量骨干网络与混合代价聚合设计，并用百万级数据的三阶段训练策略弥合仿真到真实的差距，使超轻量立体匹配模型具备零样本泛化能力，可直接用于实时深度估计与部署受限场景。
原文依据 we design a compact yet expressive backbone to ensure scalability, along with a carefully crafted hybrid cost aggregation module
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期立体匹配的进展主要聚焦于精度，往往以模型规模显著增大为代价。传统上，学界认为高效模型因容量有限而无法具备零样本能力。本文提出 Lite Any Stereo，一个在保持高度高效的同时实现强零样本泛化的立体深度估计框架。为此，我们设计了一个紧凑而富有表现力的骨干网络以保证可扩展性，并精心构造了混合代价聚合模块。我们进一步提出在百万级数据上的三阶段训练策略，以有效弥合仿真到真实的差距。上述组件共同表明，超轻量模型也能提供强泛化能力，在四个广泛使用的真实世界基准上排名第一。值得注意的是，我们的模型在计算开销不到 1% 的情况下，达到了与最优的非先验精确方法相当或更优的精度，为高效立体匹配树立了新标准。
英文原文摘要 1039 字符
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.