Full name | IterMVS |
Description | We present IterMVS, a new data-driven method for high-resolution multi-view stereo. We propose a novel GRU-based estimator that encodes pixel-wise probability distributions of depth in its hidden state. Ingesting multi-scale matching information, our model refines these distributions over multiple iterations and infers depth and confidence. To extract the depth maps, we combine traditional classification and regression in a novel manner. We verify the efficiency and effectiveness of our method on DTU, Tanks&Temples and ETH3D. While being the most efficient method in both memory and run-time, our model achieves competitive performance on DTU and better generalization ability on Tanks&Temples as well as ETH3D than most state-of-the-art methods. Code is available at https://github.com/FangjinhuaWang/IterMVS. |
Parameters | trained on DTU |
Publication title | IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo |
Publication authors | Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys |
Publication URL | https://arxiv.org/abs/2112.05126 |
Programming language(s) | python |
Hardware | 2080Ti |
Source code or download URL | https://github.com/FangjinhuaWang/IterMVS |
Submission creation date | 9 Sep, 2021 |
Last edited | 2 May, 2022 |