activity
20182022
most citedLearning Spatial Attention for Face Super-Resolution

219 citations · 339 across the 15 of their papers we have counts for

collaborators

21 papers

cs.CV202211 cited

S-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint

Wenqi Yang, Guanying Chen, Chaofeng Chen +2

In this paper, we address the "dual problem" of multi-view scene reconstruction in which we utilize single-view images captured under different point lights to learn a neural scene…

cs.CV2022

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction

Yukang Cao, Guanying Chen, Kai Han +2

This paper addresses the problem of single view 3D human reconstruction. Recent implicit function based methods have shown impressive results, but they fail to recover fine face de…

cs.CV2022

A Unified Framework for Masked and Mask-Free Face Recognition via Feature Rectification

Shaozhe Hao, Chaofeng Chen, Zhenfang Chen +1

Face recognition under ideal conditions is now considered a well-solved problem with advances in deep learning. Recognizing faces under occlusion, however, still remains a challeng…

eess.IV202122 cited

Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction

Kai Han, Kwan-Yee K. Wong, Miaomiao Liu

This paper addresses the problem of reconstructing the surface shape of transparent objects. The difficulty of this problem originates from the viewpoint dependent appearance of a…

cs.CV202112 cited

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Zhenfang Chen, Jiayuan Mao, Jiajun Wu +3

We study the problem of dynamic visual reasoning on raw videos. This is a challenging problem; currently, state-of-the-art models often require dense supervision on physical object…

cs.CV2021

HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset

Guanying Chen, Chaofeng Chen, Shi Guo +3

High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR)…