Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement
2020-06
会议录名称2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
ISSN1063-6919
页码1946-1955
发表状态已发表
DOI10.1109/CVPR42600.2020.00202
摘要Almost all previous deep learning-based multi-view stereo (MVS) approaches focus on improving reconstruction quality. Besides quality, efficiency is also a desirable feature for MVS in real scenarios. Towards this end, this paper presents a Fast-MVSNet, a novel sparse-to-dense coarse-to-fine framework, for fast and accurate depth estimation in MVS. Specifically, in our Fast-MVSNet, we first construct a sparse cost volume for learning a sparse and high-resolution depth map. Then we leverage a small-scale convolutional neural network to encode the depth dependencies for pixels within a local region to densify the sparse high-resolution depth map. At last, a simple but efficient Gauss-Newton layer is proposed to further optimize the depth map. On one hand, the high-resolution depth map, the data-adaptive propagation method and the Gauss-Newton layer jointly guarantee the effectiveness of our method. On the other hand, all modules in our Fast-MVSNet are lightweight and thus guarantee the efficiency of our approach. Besides, our approach is also memory-friendly because of the sparse depth representation. Extensive experimental results show that our method is 5 times and 14 times faster than Point-MVSNet and R-MVSNet, respectively, while achieving comparable or even better results on the challenging Tanks and Temples dataset as well as the DTU dataset. Code is available at https://github.com/svip-lab/FastMVSNet.
关键词Three-dimensional displays Memory management Image resolution Prediction algorithms Image reconstruction Optimization Feature extraction
会议地点Seattle, WA, USA
会议日期13-19 June 2020
URL查看原文
收录类别CPCI ; CPCI-S ; EI
原始文献类型Conferences
来源库IEEE
引用统计
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/122917
专题信息科学与技术学院_硕士生
信息科学与技术学院_PI研究组_高盛华组
作者单位
ShanghaiTech University
第一作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Zehao Yu,Shenghua Gao. Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement[C],2020:1946-1955.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zehao Yu]的文章
[Shenghua Gao]的文章
百度学术
百度学术中相似的文章
[Zehao Yu]的文章
[Shenghua Gao]的文章
必应学术
必应学术中相似的文章
[Zehao Yu]的文章
[Shenghua Gao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@CVPR42600.2020.00202.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。