Yibo Zhang | 张轶博

I am currently a Ph.D. student in the Intelligent Content Learning (ICL) Group at Jilin University, supervised by Professor Rui Ma , where I am also involved in joint training at the Shanghai Innovation Institute (SII).

I graduated from Jilin University in 2023 with a Bachelor degree in computer science. During undergraduate, I also interned at Zhejiang Lab, Huawei and ByteDance.

I am also a member of the PaperABC team on the Bilibili video platform, responsible for sharing cutting-edge research in 3D AIGC. Welcome to keep following us!

Email  /  Google Scholar  

profile photo

News

  • Jul. 2026   One paper is accepted by SIGGRAPH Asia 2026.
  • Jun. 2026   One paper is accepted by ECCV 2026.
  • Feb. 2025   One paper is accepted by CVPR 2025.
  • Jan. 2025   One paper is accepted by ICLR 2025.
  • Feb. 2024   One paper is accepted by CVPR 2024.

Research

My research interests lie in computer graphics and computer vision. I am particularly focused on 3D content generation and world model. Some of my papers are highlighted.

TexVerse
TexVerse: A Universe of 3D Objects with High-Resolution Textures
Yibo Zhang, Li Zhang, Rui Ma, Nan Cao
arXiv preprint
Project / Paper

We propose TexVerse, a large-scale 3D dataset featuring high-resolution textures. TexVerse collects over 858K unique high-resolution 3D models sourced from Sketchfab, including more than 158K models with physically based rendering (PBR) materials.

OmniStyle2
Learning to Stylize by Learning to Destylize: A Scalable Paradigm for Supervised Style Transfer
Ye Wang, Zili Yi, Yibo Zhang, Peng Zheng, Xuping Xie, Jiang Lin, Yilin Wang, Rui Ma
ECCV 2026
Project / Paper

We reframes artistic style transfer through destylization, a process that removes stylistic elements from artworks to recover clean, style-free content. By constructing the large-scale DST-100K dataset with this approach, we enable a simple feed-forward model that consistently surpasses state-of-the-art methods.

DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction
Miaowei Wang, Yibo Zhang, Rui Ma, Weiwei Xu, Changqing Zou, Daniel Morris
CVPR, 2025
Project / Paper

We propose DecoupledGaussian that separates static objects from their contacted surfaces in in-the-wild videos, enabling realistic object-scene interactive simulations.

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering
Yibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu, Rui Ma
ICLR, 2025
Project / Paper

We propose Diff3DS, a novel differentiable rendering framework for generating view-consistent 3D sketch. Diff3DS enables end-to-end optimization of 3D sketches via gradients in the 2D image domain, supporting novel tasks like text-to-3D sketch and image-to-3D sketch.

3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
Songchun Zhang, Yibo Zhang, Quan Zheng, Rui Ma, Wei Hua, Hujun Bao,
Weiwei Xu, Changqing Zou
CVPR, 2024
Paper

We propose 3D-SceneDreamer that provides a unified solution for text-driven 3D consistent indoor and outdoor scene generation.

Industrial Experience

Research Intern, VAST. Aug. 2025 - Present
Research Intern, Zhejiang Lab. Advised by Changqing Zou. Feb. 2023 - Aug. 2023
Algorithm Engineer Intern, Huawei. Sep. 2022 - Dec. 2022
Algorithm Engineer Intern, ByteDance. Jan. 2022 - May. 2022

Reviewer

TOG, SIGGRAPH Asia, AAAI.

Website design from Jon Barron.