I am currently an algorithm researcher at ByteDance CapCut, working on video generation and editing.
Previously, I was a senior algorithm engineer at Alibaba Group, working on 3D generation, 3D digital humans and video editing.
I obtained my Master's degree from Peking University in 2025, under the supervision of Prof. Zhouhui Lian. I was also fortunate to be advised by Prof. Peng-Shuai Wang. During my master's studies, my research focused on computer vision and computer graphics, particularly on deep generative models for 2D and 3D content, such as 3D shapes, 3D textures and vector fonts. I received my Bachelor's degree from the School of Electronics Engineering and Computer Science at Peking University in 2022.
* denotes equal contribution
CVPR 2026
project page / paper / code
A versatile and effective method tailored for expression-only video performance editing and portrait animation tasks, which has been already used in our real internal film project.
CVPR 2025
project page / paper / code
A 3D generative model trained on original 3D data from Objaverse, which is capable of generating high-quality PBR materials for input untextured 3D meshes.
CVPR 2025
project page / paper / code
An efficient method which leverages a pre-trained text-to-image diffusion Transformer and introduces structural information to generate 3D-consistent garment textures.
Computer Graphics Forum (SGP) 2025
An octree-based diffusion model to generate high-quality and high resolution 3D shapes conditioned on text prompts, sketches, or category labels.
CVPR 2023
project page / paper / code
An end-to-end trainable model to reconstruct and synthesize high-quality vector fonts using signed distance functions (SDFs).
Conference Reviewer: SIGGRAPH 2026.
Journal Reviewer: TVCG.
Email: xiongbojun AT pku.edu.cn
