SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo
Paper • 2604.04925 • Published
This repository contains weights for MVSAnywhere trained using SimpleProc data (3 different runs). See https://huggingface.co/papers/2604.04925.
“MVSAnywhere: Zero Shot Multi-View Stereo", by S. Izquierdo, M. Sayed, M. Firman, G. Garcia-Hernando, D. Turmukhambetov, J. Civera, O. Mac Aodha, G. Brostow, and J. Watson Proceedings of the Computer Vision and Pattern Recognition (CVPR), 2025”.
Commercial use is not permitted except with Niantic's permision.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support