TY - JOUR
AU1 - Zhang, Jingyang
AU2 - Li, Shiwei
AU3 - Luo, Zixin
AU4 - Fang, Tian
AU5 - Yao, Yao
AB - Learning-based multi-view stereo (MVS) methods have demonstrated promising results. However, very few existing networks explicitly take the pixel-wise visibility into consideration, resulting in erroneous cost aggregation from occluded pixels. In this paper, we explicitly infer and integrate the pixel-wise occlusion information in the MVS network via the matching uncertainty estimation. The pair-wise uncertainty map is jointly inferred with the pair-wise depth map, which is further used as weighting guidance during the multi-view cost volume fusion. As such, the adverse influence of occluded pixels is suppressed in the cost fusion. The proposed framework Vis-MVSNet significantly improves depth accuracy in reconstruction scenes with severe occlusion. Extensive experiments are performed on DTU, BlendedMVS, Tanks and Temples and ETH3D datasets to justify the effectiveness of the proposed framework.
TI - Vis-MVSNet: Visibility-Aware Multi-view Stereo Network
JF - International Journal of Computer Vision
DO - 10.1007/s11263-022-01697-3
DA - 2023-01-01
UR - https://www.deepdyve.com/lp/springer-journals/vis-mvsnet-visibility-aware-multi-view-stereo-network-tiBCKG4eHE
SP - 199
EP - 214
VL - 131
IS - 1
DP - DeepDyve
ER -