Title
StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision
Abstract
In this paper, we propose StereoPIFu, which integrates the geometric constraints of stereo vision with implicit function representation of PIFu, to recover the 3D shape of the clothed human from a pair of low-cost rectified images. First, we introduce the effective voxel-aligned features from a stereo vision-based network to enable depth-aware reconstruction. Moreover, the novel relative z-offset ...
Year
DOI
Venue
2021
10.1109/CVPR46437.2021.00060
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Keywords
DocType
ISSN
Geometry,Surface reconstruction,Computer vision,Three-dimensional displays,Shape,Robustness,Stereo vision
Conference
1063-6919
ISBN
Citations 
PageRank 
978-1-6654-4509-2
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Yang Hong101.01
Juyong Zhang237934.08
Boyi Jiang3172.06
Yudong Guo4173.67
Ligang Liu51960108.77
Hujun Bao62801174.65