About me

I am a postdoc researcher at Max Planck Institute for Informatics, advised by Prof. Christian Theobalt. I received my Ph.D. degree at Multimedia Laboratory in the Chinese University of Hong Kong in 2021, supervised by Prof. Xiaoou Tang. I also worked closely with Prof. Ping Luo and Prof. Chen Change Loy during my Ph.D. time. I obtained my Bachelor’s degree from Tsinghua University in 2016. My research interests include generative models, neural rendering, and inverse graphics.

My main works lie in X-from-GAN, which include Deep Generative Prior (DGP), GAN2Shape, ShadeGAN, Generative Occupancy Field (GOF), and GAN2X. My goal is to build systems that are able to reconstruct and synthesise the complex visual world with both high fidelity and generalizability.

Education Experience

The Chinese University of Hong Kong, HK SAR
August 2017 - July 2021
Ph.D. in Information Engineering.
Tsinghua University, Beijing, China
August 2012 - July 2016
B.E. in Automotive Engineering
GPA: 92.8, rank 1/86.

Publications

GAN2X: Non-Lambertian Inverse Rendering of Image GANs
Xingang Pan, Ayush Tewari, Lingjie Liu, Christian Theobalt
Arxiv preprint, 2022
[Paper], [Project page]

BungeeNeRF: Progressive Neural Radiance Field for Extreme Multiscale Scene Rendering
Yuanbo Xiangli*, Linning Xu*, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, Bo Dai, and Dahua Lin
European Conference on Computer Vision (ECCV), 2022
[Paper], [Project page]

Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Ayush Tewari, Mallikarjun B R, Xingang Pan, Ohad Fried, Maneesh Agrawala, Christian Theobalt
Computer Vision and Pattern Recognition (CVPR), 2022
[Paper], [Project page]

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Xingang Pan, Xudong Xu, Chen Change Loy, Christian Theobalt, Bo Dai
Advances in Neural Information Processing Systems (NeurIPS), 2021
[Code], [Paper], [Project page], [Video]

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
Xudong Xu, Xingang Pan, Dahua Lin, Bo Dai
Advances in Neural Information Processing Systems (NeurIPS), 2021
[Code], [Paper], [Project page]

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
[Code], [Paper], [Project page]

Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Yuming Jiang*, Ziqi Huang*, Xingang Pan, Chen Change Loy, Ziwei Liu
International Conference on Computer Vision (ICCV), 2021
[Code], [Paper], [Project page], [Dataset]


Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs
Xingang Pan, Bo Dai, Ziwei Liu, Chen Change Loy, Ping Luo
International Conference on Learning Representations (ICLR), 2021 (oral)
[Code], [Paper], [Project page], [Video]

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo
European Conference on Computer Vision (ECCV), 2020 (oral)
[Code], [Paper], [Project page]

Self-Supervised Scene De-occlusion
Xiaohang Zhan, Xingang Pan, Bo Dai, Ziwei Liu, Dahua Lin, Chen Change Loy
Computer Vision and Pattern Recognition (CVPR), 2020 (oral)
[Code], [Paper], [Project page]


Open Compound Domain Adaptation
Ziwei Liu*, Zhongqi Miao*, Xingang Pan, Xiaohang Zhan, Stella X. Yu, Dahua Lin, Boqing Gong
Computer Vision and Pattern Recognition (CVPR), 2020 (oral)
[Paper], [Project page]


Channel Equilibrium Networks for Learning Deep Representation
Wenqi Shao, Shitao Tang, Xingang Pan, Ping Tan, Xiaogang Wang, Ping Luo
International Conference on Machine Learning (ICML), 2020
[Paper]


Switchable Whitening for Deep Representation Learning
Xingang Pan, Xiaohang Zhan, Jianping Shi, Xiaoou Tang, Ping Luo
International Conference on Computer Vision (ICCV), 2019
[Code], [Paper]

Self-Supervised Learning via Conditional Motion Propagation
Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy
Computer Vision and Pattern Recognition (CVPR), 2019
[Code], [Paper]


Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
Xingang Pan, Ping Luo, Jianping Shi, Xiaoou Tang
European Conference on Computer Vision (ECCV), 2018
[Code], [Paper], [Supplementary]

Spatial As Deep: Spatial CNN for Traffic Scene Understanding
Xingang Pan, Jianping Shi, Ping Luo, Xiaogang Wang, Xiaoou Tang
Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018
[Dataset], [Code], [Paper], [Demo]

Professional Activities

I serve as a reviewer for CVPR, ICCV, ECCV, BMVC, NeurIPS, AAAI, and TPAMI.

Professional Experience

Max Planck Institute for Informatics, Germany
August 2021 - Now
Postdoc researcher at the Department of Visual Computing and Artificial Intelligence
The Chinese University of Hong Kong, HK SAR
October 2016 - August 2017
Junior Research Assistant at Multimedia Laboratory

Honors & Awards