Yujun Shen (Damon)



Yujun Shen is currently a senior research scientist at Ant Group, leading the Vision Intelligence Lab. Before that, he worked as a senior researcher at ByteDance Inc. He received the Ph.D. degree of Information Engineering at Multimedia Lab (MMLab), the Chinese University of Hong Kong (CUHK), and the Bachelor's degrees of Electronic Engineering and Management at Tsinghua University. His research focuses on computer vision, deep learning, and representation learning, particularly on 2D&3D generative models and the downstream applications.


  • [07/2022] Two papers (one oral) to appear at ECCV 2022.
  • [05/2022] One paper to appear at ICML 2022.
  • [03/2022] We are collecting studies on 3D generation, based on which we hope to provide an overview of this field and a better understanding on its evolution. Please stay tuned!
  • [03/2022] Four papers (one oral) to appear at CVPR 2022.
  • [02/2022] We release Hammer, a sufficiently upgraded version of GenForce, for training deep models. StyleGAN2, StyleGAN2-ADA, and StyleGAN3 are fully supported.
  • [09/2021] Two papers to appear at NeurIPS 2021.
  • [04/2021] Join ByteDance Inc. as a senior researcher.
  • [03/2021] Five papers (two oral, two workshop) to appear at CVPR 2021.
  • [12/2020] One paper got accepted by IJCV 2021.
  • [10/2020] One paper got accepted by TPAMI 2020.
  • [09/2020] We release GenForce, an efficient PyTorch library for deep generative modeling.
  • [07/2020] One paper to appear at ECCV 2020.
  • [02/2020] Two papers to appear at CVPR 2020.
  • [11/2019] Join Google (again!) as a software engineer intern.
  • [05/2019] Join Facebook Reality Lab (FRL) as a research intern.
  • [07/2018] Join Google as a software engineer intern.

Selected Publications [Full list]

One-Shot Generative Domain Adaptation
Interpreting Class Conditional GANs with Channel Awareness
3D-Aware Indoor Scene Synthesis with Depth Priors
High-fidelity GAN Inversion with Padding Space
Qingyan Bai*, Yinghao Xu*, Jiapeng Zhu, Weihao Xia, Yujiu Yang, Yujun Shen
Region-Based Semantic Factorization in GANs
3D-aware Image Synthesis via Learning Structural and Textural Representations
Improving GAN Equilibrium by Raising Spatial Awareness
Data-Efficient Instance Generation from Instance Discrimination
Low-Rank Subspaces in GANs
Jiapeng Zhu, Ruili Feng, Yujun Shen, Deli Zhao, Zhengjun Zha, Jingren Zhou, Qifeng Chen
Generative Hierarchical Features from Synthesizing Images
Closed-Form Factorization of Latent Semantics in GANs
Yujun Shen, Bolei Zhou
In-Domain GAN Inversion for Real Image Editing
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs

Professional Activities

  • Conference reviewer: CVPR, ICCV, ECCV, ICLR, SIGGRAPH, AAAI.
  • Journal reviewer: TPAMI, IJCV, TIP, Computers & Graphics, TVCJ.
  • Invited talk by Synced (机器之心).