Výsledky vyhledávání - "Wanquan Feng"

Akademický článek

Facial optical flow estimation via neural non-rigid registration

Autor: Zhuang Peng, Boyi Jiang, Haofei Xu, Wanquan Feng, Juyong Zhang

Publikováno v: Computational Visual Media, Vol 9, Iss 1, Pp 109-122 (2022)

Abstract Optical flow estimation in human facial video, which provides 2D correspondences between adjacent frames, is a fundamental pre-processing step for many applications, like facial expression capture and recognition. However, it is quite challe

Externí odkaz: https://doaj.org/article/fc4131d9163e440f983c219e7ba8979f

Zobrazit plný text záznamu

Differentiable Deformation Graph-Based Neural Non-rigid Registration

Autor: Wanquan Feng, Hongrui Cai, Junhui Hou, Bailin Deng, Juyong Zhang

Publikováno v: Communications in Mathematics and Statistics.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::803f8db1cfbb6f31c9a34d5ddc9cb6ad
https://doi.org/10.1007/s40304-023-00341-x

Zobrazit plný text záznamu

GDR-Net: A Geometric Detail Recovering Network for 3D Scanned Objects

Autor: Shiqing Xin, Juyong Zhang, Wanquan Feng, Yuanfeng Zhou

Publikováno v: IEEE transactions on visualization and computer graphics. 28(12)

This paper addresses the problem of mesh super-resolution such that the geometry details which are not well represented in the low-resolution models can be recovered and well represented in the generated high-quality models. The main challenges of th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7969e2ca4d87c4b8777db1a5573c037b
https://pubmed.ncbi.nlm.nih.gov/34495834

Zobrazit plný text záznamu

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

Autor: Hujun Bao, Hongrui Cai, Wanquan Feng, Junhui Hou, Juyong Zhang, Haofei Xu

Publikováno v: CVPR

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data. In this paper, we resolve these two challenges simultaneously. First, we propose to represent th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56593b6b625a77b569483a5168bdba7b
http://arxiv.org/abs/2011.12104