2025/01/17 by Bowen Wen, Wen, Bowen, Matthew Trepte +10 · 1 voice · 54 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Medical Image Segmentation Techniques #cs.CV #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2501.09898
openalex publication_date 2025/01/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation. Project page: https://nvlabs.github.io/FoundationStereo/