Jingzhi Bao

CUHK B.Eng., The Chinese University of Hong Kong, Shenzhen (2025)

I am a CS master student at UIUC. I received my B.Eng. in CS with first-class honor at CUHK-Shenzhen. Previously, I worked with Dr. Keyang Luo and Dr. Runze Zhang at Tencent Games, Dr. Xueting Li and Prof. Ming-Hsuan Yang at UC Merced, Prof. Guanying Chen at FNii-Shenzhen.

My research focuses on multi-modal understanding and 3D foundation models. I am currently working on technical scaling of foundation models to production-ready standards.

portrait
GitHub WeChat LinkedIn
Education
  • University of Illinois Urbana-Champaign (UIUC)

    University of Illinois Urbana-Champaign (UIUC)

    Master in Computer Science Sep. 2025 - Present

  • The Chinese University of Hong Kong, Shenzhen

    The Chinese University of Hong Kong, Shenzhen

    B.Eng. in Computer Science and Engineering Sep. 2021 - July 2025

  • Nanyang Technological University (NTU)

    Nanyang Technological University (NTU)

    Exchange Student Aug. 2023 - Dec. 2023

Experience
  • Lightspeed Studios, Tencent Games

    Lightspeed Studios, Tencent Games

    Research Intern Feb. 2025 - Aug. 2025

  • MeshyAI

    MeshyAI

    Research Collaboration 2025

  • University of California, Merced

    University of California, Merced

    Visiting Student June 2024 - Dec. 2024

  • Future Network of Intelligence Institute (FNii)

    Future Network of Intelligence Institute (FNii)

    Research Intern July 2023 - Dec. 2023

Publications
LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

Jingzhi Bao*, Hongze Chen*, Lingting Zhu, Chenyu Liu, Runze Zhang, Keyang Luo, Zeyu Hu, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang, Xiaoguang Han

International Conference on Learning Representations (ICLR), 2026

A product-ready level PBR generation method that surpasses SoTA open-source and commercial methods (Hunyuan3D 2.1, Meshy-6, Tripo AI v3).

arXiv arXiv Project Page Code

LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

Jingzhi Bao*, Hongze Chen*, Lingting Zhu, Chenyu Liu, Runze Zhang, Keyang Luo, Zeyu Hu, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang, Xiaoguang Han

International Conference on Learning Representations (ICLR), 2026

A product-ready level PBR generation method that surpasses SoTA open-source and commercial methods (Hunyuan3D 2.1, Meshy-6, Tripo AI v3).

arXiv arXiv Project Page Code

CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation

Chenyu Liu, Hongze Chen, Jingzhi Bao, Lingting Zhu, Runze Zhang, Weikai Chen, Zeyu Hu, Yingda Yin, Keyang Luo, Xin Wang

arXiv preprint, 2025

A framework of geometry-calibrated attention (geo-aligned attention + condition-routed attention) achieves strong texture alignment with 3D structure. CaliTex produces cross-view consistent textures ourperforming both open-source and commercial methods (Hunyuan3D 2.1/3.0).

arXiv arXiv Project Page

CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation

Chenyu Liu, Hongze Chen, Jingzhi Bao, Lingting Zhu, Runze Zhang, Weikai Chen, Zeyu Hu, Yingda Yin, Keyang Luo, Xin Wang

arXiv preprint, 2025

A framework of geometry-calibrated attention (geo-aligned attention + condition-routed attention) achieves strong texture alignment with 3D structure. CaliTex produces cross-view consistent textures ourperforming both open-source and commercial methods (Hunyuan3D 2.1/3.0).

arXiv arXiv Project Page

Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models

Jingzhi Bao, Xueting Li, Ming-Hsuan Yang

arXiv preprint, 2024

We present Tex4D, a zero-shot framework that fuses 3D geometric priors from mesh sequences with the generative power of video diffusion models to produce multi-view, temporally consistent 4D textures.

arXiv arXiv Project Page

Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models

Jingzhi Bao, Xueting Li, Ming-Hsuan Yang

arXiv preprint, 2024

We present Tex4D, a zero-shot framework that fuses 3D geometric priors from mesh sequences with the generative power of video diffusion models to produce multi-view, temporally consistent 4D textures.

arXiv arXiv Project Page

Photometric Inverse Rendering: Shading Cues Modeling and Reflectance Regularization
Photometric Inverse Rendering: Shading Cues Modeling and Reflectance Regularization

Jingzhi Bao, Guanying Chen, Shuguang Cui

International Conference on 3D Vision (3DV), 2025

A differentiable inverse rendering framework that jointly optimizes lighting and materials for photometric images, achieving accurate self-shadow handling and inter-reflection estimation. DINO-based feature distillation delivers more consistent surface reflectance decomposition.

arXiv arXiv Project Page Code

Photometric Inverse Rendering: Shading Cues Modeling and Reflectance Regularization
Photometric Inverse Rendering: Shading Cues Modeling and Reflectance Regularization

Jingzhi Bao, Guanying Chen, Shuguang Cui

International Conference on 3D Vision (3DV), 2025

A differentiable inverse rendering framework that jointly optimizes lighting and materials for photometric images, achieving accurate self-shadow handling and inter-reflection estimation. DINO-based feature distillation delivers more consistent surface reflectance decomposition.

arXiv arXiv Project Page Code