Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching

Junpeng Jing; Ronglai Zuo; Zhelun Shen; Shangchen Zhou; Rolandos Alexandros Potamias; Stefanos Zafeiriou; Krystian Mikolajczyk; Jiankang Deng

title

authors

Junpeng Jing, Ronglai Zuo, Zhelun Shen, Shangchen Zhou, Rolandos Alexandros Potamias, Stefanos Zafeiriou, Krystian Mikolajczyk, Jiankang Deng

date

2026-06-23

venue

arXiv (preprint, not peer reviewed)

arXiv:2606.24457

affiliation

Imperial College London

upvotes

4 (Hugging Face Daily Papers, 2026-11-01)

links

abs pdf hf code

abstract

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/.

@misc{jing2026lite,
  title={Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching},
  author={Junpeng Jing and Ronglai Zuo and Zhelun Shen and Shangchen Zhou and Rolandos Alexandros Potamias and Stefanos Zafeiriou and Krystian Mikolajczyk and Jiankang Deng},
  year={2026},
  eprint={2606.24457},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.24457}
}