Filters








3 Hits in 3.7 sec

PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility [article]

Jae Yong Lee, Joseph DeGol, Chuhang Zou, Derek Hoiem
2021 arXiv   pre-print
, normals, and visibility.  ...  Recent learning-based multi-view stereo (MVS) methods show excellent performance with dense cameras and small depth ranges.  ...  We propose PatchMatch-RL, an end-to-end trainable PatchMatch-based MVS approach that combines advantages of trainable costs and regularizations with pixelwise estimates of depth, normal, and visibility  ... 
arXiv:2108.08943v1 fatcat:47vla23zoveifdaywzdokaxsoe

IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo [article]

Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys
2021 arXiv   pre-print
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.  ...  Patchmatch-rl: Deep mvs with pixelwise depth, nor- depth-maps for multi-view stereo.  ... 
arXiv:2112.05126v1 fatcat:hwlfy6g5xvbzbkww5e2zihxthm

Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo [article]

Jiayu Yang, Jose M. Alvarez, Miaomiao Liu
2022 arXiv   pre-print
In contrast, we propose constructing the cost volume by non-parametric depth distribution modeling to handle pixels with unimodal and multi-modal distributions.  ...  Recent cost volume pyramid based deep neural networks have unlocked the potential of efficiently leveraging high-resolution images for depth inference from multi-view stereo.  ...  Related works Deep Learning-based MVS methods adopt deep CNNs to infer the depth map for each view followed by a separate multiple-view fusion process for building 3D models.  ... 
arXiv:2205.03783v1 fatcat:siyzfen2zjdhflllwwcnf743pa