Jingzhi Bao
B.Eng., The Chinese University of Hong Kong, Shenzhen (2025)
I am a final-year undergrad. major in Computer Science at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen). Currently, I am a technical research intern focusing on 3D assets generation at LightSpeed & Quantum Studios, Tencent IEG.
My research focuses on generative models, animation, inverse graphics, and 3D reconstruction. It's my greate fortune to work with Dr. Xueting Li and Prof. Ming-Hsuan Yang at University of California, Merced. Previously, I also worked with Prof. Guanying Chen at FNii-Shenzhen.
Education
-
The Chinese University of Hong Kong, Shenzhen
B.Eng. in Computer Science and Engineering Sep. 2021 - Jul. 2025
-
Nanyang Technological University (NTU)
Exchange Student Aug. 2023 - Dec. 2023
Experience
-
Lightspeed & Quantum Studios, Tencent
Technical Research Intern Feb. 2025 - Present
-
University of California, Merced
Visiting Student June 2024 - Jan. 2025
-
Future Network of Intelligence Institute (FNii)
Research Intern July 2023 - April 2024
Publications
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models
Jingzhi Bao, Xueting Li, Ming-Hsuan Yang
Under review. 2024
We present Tex4D, a zero-shot approach that integrates inherent 3D geometry knowledge from mesh sequences with the expressiveness of video diffusion models to produce multi-view and temporally consistent 4D textures. Given an untextured mesh sequence and a text prompt as inputs, our method generates multi-view, temporally consistent 4D textures.
arXivTex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models
Jingzhi Bao, Xueting Li, Ming-Hsuan Yang
Under review. 2024
We present Tex4D, a zero-shot approach that integrates inherent 3D geometry knowledge from mesh sequences with the expressiveness of video diffusion models to produce multi-view and temporally consistent 4D textures. Given an untextured mesh sequence and a text prompt as inputs, our method generates multi-view, temporally consistent 4D textures.
Photometric Inverse Rendering: Shading Cues Modeling and Surface Reflectance Regularization
Jingzhi Bao, Guanying Chen, Shuguang Cui
International Conference on 3D Vision (3DV), 2025
This paper addresses the problem of inverse rendering from photometric images. Our method jointly optimizes the light source position to account for the self-shadows in images, and computes indirect illumination using a differentiable rendering layer and an importance sampling strategy. To enhance surface reflectance decomposition, we introduce a new regularization by distilling DINO features to foster accurate and consistent material decomposition.
Photometric Inverse Rendering: Shading Cues Modeling and Surface Reflectance Regularization
Jingzhi Bao, Guanying Chen, Shuguang Cui
International Conference on 3D Vision (3DV), 2025
This paper addresses the problem of inverse rendering from photometric images. Our method jointly optimizes the light source position to account for the self-shadows in images, and computes indirect illumination using a differentiable rendering layer and an importance sampling strategy. To enhance surface reflectance decomposition, we introduce a new regularization by distilling DINO features to foster accurate and consistent material decomposition.