Jun Xiang (项 军)

I am a fifth-year Ph.D. student in Graphics & Geometric Computing Laboratory (GCL) at University of Science and Technology of China (USTC) supervised by Prof. Juyong Zhang. I obtained my B.S. degree in Mathematics in 2021 from USTC. And I undertook an internship in Image Derivative Inc. during Mar.2022-Jun.2023, also served as a research assistant at The Hong Kong Polytechnic University (PolyU) guided by Prof. Defeng Sun and Yancheng Yuan during Sep.2024-Sep.2025.

I am looking for formal job opportunities in 2026 / 2027 !

My research interests include but are not limited to:

• Avatar Reconstruction and Generation

• Neural Representation and 3D Vision

• Video Generation and Spatial Computing

One Shot, One Talk: Whole-body Talking Avatar from a Single Image
Jun Xiang, Yudong Guo, Leipeng Hu, Boyang Guo, Yancheng Yuan, Juyong Zhang.

IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
project page / paper / code (coming soon)

Our method reconstructs an expressive whole-body animatable talking avatar from a one-shot image.

FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding
Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang.

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
project page / paper / code

We attach 3DGS on mesh UV space to achieve 300FPS head avatar rendering.

Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video
Xuan Gao, Chenglai Zhong, Jun Xiang, Yang Hong, Yudong Guo, Juyong Zhang.

ACM Transactions on Graphics (SIGGRAPH ASIA), Vol.41, No.6, 2022.
project page / paper / code