Journal
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
Volume -, Issue -, Pages 4311-4320Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ICCV.2019.00441
Keywords
-
Funding
- National Natural Science Foundation of China [61673234]
Ask authors/readers for more resources
We present a deep-learning architecture for multi-view stereo with conditional random fields (MVSCRF). Given an arbitrary number of input images, we first use a U-shape neural network to extract deep features incorporating both global and local information, and then build a 3D cost volume for the reference camera. Unlike previous learning-based methods, we explicitly constraint the smoothness of depth maps by using conditional random fields (CRFs) after the stage of cost volume regularization. The CRFs module is implemented as recurrent neural networks so that the whole pipeline can be trained end-to-end. Our results show that the proposed pipeline outperforms previous state-of-the-arts on large-scale DTU dataset. We also achieve comparable results with state-of-the-art learning-based methods on outdoor Tanks and Temples dataset without fine-tuning, which demonstrates our method's generalization ability.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available