IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo
This work addresses efficient 3D reconstruction for computer vision applications, offering incremental improvements in generalization and efficiency over existing methods.
The paper tackles high-resolution multi-view stereo by proposing IterMVS, a data-driven method using a GRU-based estimator to iteratively refine depth probability distributions, achieving competitive performance on DTU and better generalization on Tanks&Temples and ETH3D while being the most efficient in memory and runtime.
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.