MVSAnywhere: Zero-Shot Multi-View Stereo

Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision. However, most existing approaches do not generalize well across different domains and scene types (e.g. indoor vs. outdoor). Training a general-purpose multi-view stereo model is challenging and raises several questions, e.g. how to best make use of transformer-based architectures, how to incorporate additional metadata when there is a variable number of input views, and how to estimate the range of valid depths which can vary considerably across different scenes and is typically not known a priori? To address these issues, we introduce MVSA, a novel and versatile Multi-View Stereo architecture that aims to work Anywhere by generalizing across diverse domains and depth ranges. MVSA combines monocular and multi-view cues with an adaptive cost volume to deal with scale-related issues. We demonstrate state-of-the-art zero-shot depth estimation on the Robust Multi-View Depth Benchmark, surpassing existing multi-view stereo and monocular baselines.

@article{izquierdo2025_2503.22430,
  title={ MVSAnywhere: Zero-Shot Multi-View Stereo },
  author={ Sergio Izquierdo and Mohamed Sayed and Michael Firman and Guillermo Garcia-Hernando and Daniyar Turmukhambetov and Javier Civera and Oisin Mac Aodha and Gabriel Brostow and Jamie Watson },
  journal={arXiv preprint arXiv:2503.22430},
  year={ 2025 }
}