Lite Any Stereo V2：更快更強的零樣本高效立體匹配

摘要

近期立體匹配領域的進展已實現卓越精準度，但通常依賴大型模型、大量運算或額外基礎模型先驗知識，使其難以部署於資源受限平台。相較之下，高效立體模型雖能提供更快的推論速度，但普遍被認為在零樣本泛化能力上較弱。本文透過提出Lite Any Stereo V2（LAS2）系列超高速模型來挑戰此觀點，該系列專為高效的零樣本立體匹配設計。LAS2從架構與訓練兩個層面進行開發。架構方面，我們在實際部署情境下重新審視高效立體設計，並提出僅以二維影像為基礎的代價聚合框架，其優化目標為實際推論延遲而非理論上的MAC值。訓練方面，我們發展出三階段策略，結合合成資料監督、自我蒸餾與真實世界知識蒸餾。為提升真實世界偽監督的可靠性，我們進一步導入偽標籤濾波與誤差限制操作，實現更平滑的合成資料到真實資料轉移。我們將LAS2實例化為一系列模型，包括針對不同效率需求的饋送式變體，以及追求更高精準度的迭代式變體。大量實驗顯示，LAS2在維持顯著更低延遲的同時，達到了高效立體方法中的最佳精準度。具體而言，LAS2-H的整體零樣本效能優於迭代式方法Fast-FoundationStereo，在H200與Orin平台上分別實現1.8倍與2.7倍的推論加速。專案頁面、展示與程式碼均已公開於 https://tomtomtommi.github.io/LiteAnyStereoV2/。

English

Recent advances in stereo matching have achieved remarkable accuracy, but often rely on large models, heavy computation, or additional foundation-model priors, making them difficult to deploy on resource-constrained platforms. In contrast, efficient stereo models offer faster inference but are commonly considered less capable of strong zero-shot generalization. In this paper, we challenge this assumption by introducing Lite Any Stereo V2 (LAS2), an ultra-fast model series designed for efficient zero-shot stereo matching. LAS2 is developed from both architecture and training perspectives. Architecturally, we revisit efficient stereo design under practical deployment settings and propose a 2D-only cost aggregation framework, optimized for real inference latency rather than theoretical MACs alone. For training, we develop a three-stage strategy that combines synthetic supervision, self-distillation, and real-world knowledge distillation. To improve the reliability of real-world pseudo supervision, we further introduce pseudo-label filtering and an error-clamping operation, enabling smoother synthetic-to-real transfer. We instantiate LAS2 as a family of models, including feed-forward variants for different efficiency budgets and an iterative variant for higher accuracy. Extensive experiments show that LAS2 achieves state-of-the-art accuracy among efficient stereo methods while maintaining significantly lower latency. Specifically, LAS2-H achieves stronger overall zero-shot performance than the iterative method Fast-FoundationStereo, with 1.8x and 2.7x faster inference on H200 and Orin, respectively. The project page, demos, and code are available at https://tomtomtommi.github.io/LiteAnyStereoV2/.