Dejia Xu

Dejia Xu

Auto-generated profile, based on publicly available information

Dejia Xu

The University of Texas at Austin, Austin, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
DXDejia Xu
Dejia Xu
YJYifan Jiang
Yifan Jiang
PWPeihao Wang
Peihao Wang
ZFZhiwen Fan
Zhiwen Fan
HSHumphrey Shi
Humphrey Shi
ZWZhangyang (Atlas) Wang
Zhangyang (Atlas) Wang

31 October 2022
Verified
Book Chapter
Closed access
PDF file
ZFZhiwen Fan
Zhiwen Fan
YJYifan Jiang
Yifan Jiang
PWPeihao Wang
Peihao Wang
XGXinyu Gong
Xinyu Gong
DXDejia Xu
Dejia Xu
ZWZhangyang (Atlas) Wang
Zhangyang (Atlas) Wang

2 October 2024
Verified
Book Chapter
Closed access
PDF file
SZShijie Zhou
Shijie Zhou
ZFZhiwen Fan
Zhiwen Fan
DXDejia Xu
Dejia Xu
HCHaoran Chang
Haoran Chang
PCPradyumna Chari
Pradyumna Chari
AKAchuta Kadambi
Achuta Kadambi

26 October 2023
Verified
Conference Paper
Open access
YYYuyang Yin
Yuyang Yin
DXDejia Xu
Dejia Xu
CTChuangchuang Tan
Chuangchuang Tan
PLPing Liu
Ping Liu
YZYao Zhao
Yao Zhao
YWYunchao Wei
Yunchao Wei

23 February 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
CWCe Wang
Ce Wang
DXDejia Xu
Dejia Xu
RWRenjie Wan
Renjie Wan
BHBin He
Bin He
BSBoxin Shi
Boxin Shi
LDLing-Yu Duan
Ling-Yu Duan
Colored glass, which is commonly seen in modern city life, often degrades images taken through it with co-occurring reflection and color bias due to its optical property of simultaneous transmission, reflection, and wavelength-selective absorption.~Recovering the clean background behind colored glass is inherently challenging due to the mutual interference of two degradations within a single mixture observation, and has barely been specifically considered by existing image restoration methods. In this paper, we aim at realizing faithful background scene recovery for an image taken in front of colored glass. We first analyze the formation model of mixed degradations caused by colored glass, and propose a cooperative framework to address the mutual interference problem, featuring a novel glass color invariant loss and progressive refinement. Besides, we propose a data synthesis strategy for network training. Experimental results on our newly collected real-world dataset show that our proposed method achieves state-of-the-art performance.

30 June 2025
Verified
Conference Paper
Open access
EPElia Peruzzo
Elia Peruzzo
DXDejia Xu
Dejia Xu
XXXingqian Xu
Xingqian Xu
HSHumphrey Shi
Humphrey Shi
NSNicu Sebe
Nicu Sebe