Yujie Wang

Yujie Wang

Postdoctoral Researcher in Computer Science
yujiew.cn@gmail.com
UNC-Chapel Hill, North Carolina

About Me

I am currently a postdoctoral researcher in Computer Science at the University of North Carolina at Chapel Hill, hosted by Prof. Praneeth Chakravarthula.

I received my Ph.D. in 2024 from Shandong University, where I was supervised by Prof. Baoquan Chen, with most of my research conducted at the Visual Computing and Learning Lab (VCL), Peking University.

Prior to that, I earned my M.S. from Tianjin University and completed my undergraduate studies at Sichuan University.

My research interests lie in 3D scene reconstruction and generation, as well as computer-generated holography.

3D Scene Reconstruction & Generation Computer-Generated Holography

Publications

DOF-GS

DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal

Yujie Wang, Praneeth Chakravarthula and Baoquan Chen
The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
Paper Project Page Github Repo
Canonicalization

One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency

Li Jin, Yujie Wang, Wenzheng Chen, Qiyu Dai, Qingzhe Gao, Baoquan Chen and Xueyin Qin
The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
Paper Project Page Github Repo
HoloZip

Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts

Debabrata Mandal, Zhihan Peng,Yujie Wang and Praneeth Chakravarthula
The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026
Paper
HoloZip

HoloZip: High Hologram Compression via Latent-of-Latent Coding

Huaizhi Qu*, Yujie Wang*, Ruichen Zhang, Hengyu Lian, Mufan Qiu, Samarjit Chakraborty, Henry Fuchs, Tianlong Chen and Praneeth Chakravarthula
IEEE International Conference on Computational Photography (ICCP), 2025
Paper
PupilAdaptive

Pupil-Adaptive 3D Holography Beyond Coherent Depth-of-Field

Yujie Wang, Baoquan Chen and Praneeth Chakravarthula
Arxiv, 2024
Paper
Holography
🏆 Best Paper Honorable Mention

Joint Neural Phase Retrieval and Compression for Energy- and Computation-Efficient Holography on the Edge

Yujie Wang*, Praneeth Chakravarthula*, Qi Sun and Baoquan Chen
ACM Transactions on Graphics (presented at SIGGRAPH 2022 and IEEE VIS 2022)
Paper Code
SinGRAV

SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scene

Yujie Wang, Xuelin Chen and Baoquan Chen
Journal of Computer Science and Technology, 2024 (Arxiv, 2022.)
Paper Project Page
Intrinsic Data

High Quality Rendered Dataset and Non-local Graph Convolutional Network for Intrinsic Image Decomposition

Yujie Wang, Qingnan Fan, Kun Li, Dongdong Chen, Jingyu Yang, Jianzhi Lu, Dani Lischinski and Baoquan Chen
Journal of Image and Graphics (Chinese), 2022
Paper Dataset and Bibtex Paper (PDF, English version)
Sparse Intrinsic

Sparse intrinsic decomposition and applications

Kun Li*, Yujie Wang*, Xinchen Ye, Chenggang Yan, and Jingyu Yang
Signal Processing: Image Communication, 2021
Paper Code and Bibtex
ICME 2017
🏆 Best Paper Award

Intrinsic decomposition from a single RGB-D image with sparse and non-local priors

Yujie Wang, Kun Li, Jingyu Yang and Xinchen Ye
IEEE International Conference on Multimedia and Expo, ICME 2017, Hongkong, China.
Paper Code

Research Experience

Postdoctoral Researcher
UNC-Chapel Hill, USA
Chapel Hill, North Carolina, USA
2024.12 - Present
Research Scholar
Peking University, China
Beijing, China
2024.04 - 2024.11
Visiting Student
Peking University, China
Beijing, China
2021.07 - 2024.03
Intern
AICFVE Research
Beijing, China
2018.07 - 2021.07

Awards

World's FIRST 10K Best Paper Award
IEEE International Conference on Multimedia and Expo, ICME 2017
2017
National Scholarship
Ministry of Education of China