NPF-MVSNet: Normal and Pyramid Feature Aided Unsupervised MVS Network
We proposed an unsupervised learning-based network, named NPF-MVSNet, for multi-view stereo reconstruction without ground-truth 3D training data. Our network put forward: (a)The pyramid feature aggregation to capture more contextual information for cost volume construction; (b) Normal-depth consistency to make estimated depth maps more reasonable and precise in the real 3D world; (c) the combination of pixel-wise and feature-wise loss function to learning the inherent constraint from the perspective of perception beyond the pixel value. The experiments have proved the state of arts of NPF-MVSNet and each innovation insights contributes to the network with effective improvement. The excellent generalization ability of our network without any finetuning is shows in the leaderboard of Tanks & Temples datasets. NPF-MVSNet is the best unsupervised MVS network with limited GPU memory consumption until April 17, 2020. Our codebase is available at https://github.com/whubaichuan/NPF-MVSNet.
READ FULL TEXT