IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo
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.
Code (1)
Tasks
regressionSimilar Papers 제목 키워드 기반
Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation
3D human pose estimation has been a long-standing challenge in computer vision and graphics, where multi-view methods have significantly progressed but are limited by the tedious calibration processes. Existing multi-vie…
3D Human Pose Estimation3D Pose EstimationMulti-view 3D Human Pose EstimationPose EstimationIDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting
Generalizable 3D Gaussian Splatting aims to directly predict Gaussian parameters using a feed-forward network for scene reconstruction. Among these parameters, Gaussian means are particularly difficult to predict, so dep…
Depth EstimationSelf-Learning Symmetric Multi-view Probabilistic Clustering
Multi-view Clustering (MVC) has achieved significant progress, with many efforts dedicated to learn knowledge from multiple views. However, most existing methods are either not applicable or require additional steps for …
ClusteringIncomplete multi-view clusteringSelf-LearningMulti-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
Multi-view depth estimation methods typically require the computation of a multi-view cost-volume, which leads to huge memory consumption and slow inference. Furthermore, multi-view matching can fail for texture-less sur…
Depth EstimationExploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation
Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentall…
AllDepth EstimationDepth PredictionOptical Flow Estimation