Yinghao Xu Ph.D. Student Department of Information Engineering The Chinese University of Hong Kong E-mail  /  Github  /  Twitter  /  CV

Biography

Yinghao Xu is a fourth-year Ph.D. student at Multimedia Lab (MMLab), Department of Information Engineering in The Chinese University of Hong Kong. His supervisor is Prof. Dahua Lin and he worked closely with Prof. Bolei Zhou. He is very interested in generative models for visual understanding and content recreation, particularly in 3D generative models. He also collaborates with Dr. Bo Dai, Dr. Yujun Shen and Dr. Ceyuan Yang.

Before that, he obtained bachelor degree in Information Engineering from Zhejiang University in 2019, advised by Dr. Lechao Cheng and Prof. Chunguang Li.

News

• [03/2023] DiscoScene is selected as the Highlight paper!
• [02/2023] Three papers are accepted by CVPR 2023!
• [01/2023] Two papers with one oral (3DGP), are accepted by ICLR 2023!
• [12/2022] DiscoScene is released in arxiv.
• [11/2022] The extension of GHFeat got accepted by TPAMI.
• [10/2022] We post the survey on 3D generative models.
• [09/2022] Two papers, with one spotlight, will appear at NeurIPS 2022.
• [07/2022] Give a talk about 3D generative models at Stanford Computational Imaging Lab.
• [07/2022] SSP-NeRF (Oral) and PadInv are accepted by ECCV 2022.
• [05/2022] ReSeFa is accepted by ICML 2022.
• [03/2022] CMPL is accepted as an oral paper by CVPR 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 are accepted by 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] One paper to appear in NeurIPS 2021. It is my first NeurIPS paper.
• [03/2021] One paper about object-level nerf is accepted by ICCV 2021.
• [03/2021] Two papers (one oral and one best paper candidate) to appear in CVPR 2021.
• [09/2020] We release GenForce, an efficient PyTorch library for deep generative modeling.

Selected Publications [Full List] [Oral/Spotlight]

	DiscoScene: Spatially Disentangled Generative Radiance Field for Controllable 3D-aware Scene Synthesis Yinghao Xu, Menglei Chai, Zifan Shi, Sida Peng, Ivan Skorokhodov, Aliaksandr Siarohin, Ceyuan Yang, Yujun Shen, Hsin-Ying Lee, Bolei Zhou, Sergey Tulyakov. CVPR 2023 / Project / Code / Final scores: 5, 5, 5 Highlight Presentation
	Learning 3D-aware Image Synthesis with Unknown Pose Distribution Zifan Shi*, Yujun Shen*, Yinghao Xu, Sida Peng, Yiyi Liao, Sheng Guo, Qifeng Chen, Dit-Yan Yeung. CVPR 2023 / Project / Code
	GLeaD: Improving GANs with A Generator-Leading Task Qingyan Bai, Ceyuan Yang, Yinghao Xu, Xihui Liu, Yujiu Yang, Yujun Shen. CVPR 2023 / Project / Code
	Deep Generative Models on 3D Representations: A Survey Zifan Shi*, Sida Peng*, Yinghao Xu*, Yiyi Liao, Yujun Shen. Paper / Github
	One-Shot Generative Domain Adaptation Ceyuan Yang*, Yujun Shen*, Zhiyi Zhang, Yinghao Xu, Jiapeng Zhu, Zhirong Wu, Bolei Zhou. Paper / Code I love this paper!
	3D Generation on ImageNet Ivan Skorokhodov, Aliaksandr Siarohin, Yinghao Xu, Jian Ren, Hsin-Ying Lee, Peter Wonka, Sergey Tulyakov. ICLR 2023 / Paper / Project / Code Oral Presentation
	Towards Smooth Video Composition Qihang Zhang, Ceyuan Yang, Yujun Shen, Yinghao Xu, Bolei Zhou. ICLR 2023 / Paper / Project / Code
	GH-Feat: Learning Versatile Generative Hierarchical Features from GANs Yinghao Xu, Yujun Shen, Jiapeng Zhu, Ceyuan Yang, Bolei Zhou. TPAMI 2022 / Paper / Project / Code
	Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator Zifan Shi, Yinghao Xu, Yujun Shen, Deli Zhao, Qifeng Chen, Dit-Yan Yeung. NeurIPS 2022 / Project / Code Spotlight Presentation
	High-fidelity GAN Inversion with Padding Space Qingyan Bai*, Yinghao Xu*, Jiapeng Zhu, Weixiao Xia, Yujiu Yang, Yujun Shen. ECCV 2022 / Project / Code
	Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation Xian Liu, Yinghao Xu, Qianyi Wu, Hang Zhou, Wayne Wu, Bolei Zhou. ECCV 2022 / Project / Code Oral Presentation
	Region-Based Semantic Factorization in GANs Jiapeng Zhu, Yujun Shen, Yinghao Xu, Deli Zhao, Qifeng Chen. ICML 2022 / Paper / Code
	3D-aware Image Synthesis via Learning Structural and Textural Representations Yinghao Xu, Sida Peng, Ceyuan Yang, Yujun Shen, Bolei Zhou. CVPR 2022 / Paper / Project / Code
	Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition Yinghao Xu, Fangyun Wei, Xiao Sun, Ceyuan Yang, Yujun Shen, Bo Dai, Bolei Zhou, Stephen Lin. CVPR 2022 / Paper / Project Oral Presentation
	Generative Hierarchical Features from Synthesizing Images Yinghao Xu*, Yujun Shen*, Jiapeng Zhu, Ceyuan Yang, Bolei Zhou. CVPR 2021 / Paper / Project / Code Oral Presentation
	Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou. CVPR 2021 / Paper / Project / Code Best paper candidate
	Unsupervised Landmark Learning from Unpaired Data Yinghao Xu*, Ceyuan Yang*, Ziwei Liu, Bo Dai, Bolei Zhou. Paper / Code
	Dense RepPoints: Representing Visual Objects with Dense Point Sets Yinghao Xu*, Ze Yang*, Han Xue*, Zheng Zhang, Raquel Urtasun, Liwei Wang, Steve Lin, Han Hu. ECCV 2020 / Paper / Code
	Temporal Pyramid Network for Action Recognition Ceyuan Yang*, Yinghao Xu*, Jianping Shi, Bo Dai, Bolei Zhou. CVPR 2020 / Paper / Code
	A Main/Subsidiary Network Framework for Simplifying Binary Networks Yinghao Xu, Xin Dong, Yudian Li, Hao Su. CVPR 2019 / Paper / Code

Experiences

	Research Intern, Snap Inc. Jul. 2022 - Oct. 2022 Host by Menglei Chai
	Student Researcher, ByteDance Inc. Jul. 2021 - Feb. 2022 Host by Yujun Shen
	Student Researcher, Microsoft Research Asia Mar. 2021 - Jun. 2021 Host by Fangyun Wei, Xiao Sun, Steve Lin
	Research Intern, Microsoft Research Asia Nov. 2018 - May. 2019 Host by Jifeng Dai, Han Hu, Steve Lin
	Research Assistant, U.C. San Diego Jul. 2018 - Sep. 2019 Host by Hao Su

Invited Talks

• Stanford Computational Imaging Lab: Towards Efficient and High-Quality 3D-Aware Image Synthesis.
  2022
• TechBeat: 3D-aware Image Synthesis via Learning Structural and Textural Representations.
  2022
• AI TIME: Learning Deep Representations by Unifying Discriminative and Generative Models.
  2021
• TechBeat: Generative Hierarchical Features from Synthesizing Images.
  2021

Professional activities

• Conference Reviewer for CVPR, ECCV, AAAI, ICCV, NIPS, ICLR, ICML, SIGGRAPH

Selected Honors & Awards

• National Scholarship,
  2018
• Tang Lixin Scholarship,
  2018
• First Class Scholarship for Academic Excellence,
  2018, 2017
• Government Scholarship of Zhejiang Province,
  2017, 2016
• Meritorious Winner, Interdisciplinary Contest In Modeling(ICM),
  2018
• First Prize of Mathematics Competition of Chinese College Students,
  2017