Author(s):
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys
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.
Method parameters:
trained on BlendedMVS
Used image set:
Reconstructions from provided image set
Publication:
https://arxiv.org/abs/2112.05126
Software or method website:
https://github.com/FangjinhuaWang/IterMVS
Error Visualization:
| Precision | Recall |