Yuliang Xiu 修宇亮 Max Planck Institute for Intelligent Systems yuliang.xiu tue.mpg.de |

Biography I will join Westlake University (AI) as a tenure-track Assistant Professor in Spring 2025, and lead 远兮实验室 (endless.do) as PI. I am actively recruiting 25Fall PhD, RA ( >6 months, research oriented ) and visiting student ( target for 26Fall PhD@Westlake ). If you are interested, please complete the Google Form, then send the required materials to Email, as outlined in Recruitment I am currently a final Year Ph.D. student (2020.11 - Now), working in Perceiving Systems, Max Planck Institute for Intelligent Systems (MPI-IS), with Michael J. Black and Dimitrios Tzionas. As a Marie Sklodowska-Curie Fellow (MSCA) of CLIPE (ESR 11), I work on Democratizing Human-centric Digitization in computer vision, computer graphics and machine learning. Human-centric. Human is the measure of all things As intellectual beings, humans shape the world to our will. If we agree that pursuing AGI (Artificial General Intelligence) is valuable -- where agents can perform any intellectual task as well as or better than us, then learning skillsets through simulating lifelike virtual humans could be a critical baby step. Digitization. What I cannot create, I do not understand Compared to text and images, the digitization of the 3D world is underdeveloped due to the costly and time-consuming process of capturing or synthesizing. Specifically, the challenge of creating 3D digital humans with photorealistic appearances, lifelike movements, and faithful personalities in a scalable manner remains unresolved. Democratization. Immortality stems from generalization I am always intrigued by ideas that are conceptually intuitive yet practically applicable. Great models should be truly generalizable, scalable on large-scale raw data, accessible to the general public, and ultimately benefit all of humanity. I was briefly enrolled (2019.9-2020.10) as a Ph.D. student in Vision and Graphics Lab at University of Southern California, advised by Hao Li. I got M.Sc. degree at Shanghai Jiao Tong University in 2019, working in Machine Vision and Intelligence Group, advised by Cewu Lu, and got B.Eng. degree in Digital Media Technology at Shandong University in 2016, worked closely with Lu Wang. I spent wonderful time at USC Institute for Creative Technology with Jun Xing, at Kwai Y-tech with Chongyang Ma, at LightChaser Animation Studio with Xinxin Zhang, and at Ubisoft La Forge. I am interning at Meta Reality Labs with Shunsuke Saito.

News Follow @yuliangxiu

[2024/10/19] Please check out our Stable-X HuggingFace demos: StableNormal, StableRecon, and StableDelight.
[2024/08/29] Invited talk "Democratizing Human Digitization from Casual Photos" at GAMES Webinar
[2024/07/28] PuzzleAvatar and StableNormal both get accepted by SIGGRAPH Asia 2024 (Journal), see you in Tokyo.
[2024/07/22] I start the internship at Reality Labs Research @ Meta, working with Shunsuke Saito, see you at Pittsburgh.
[2024/07/02] I will serve as the Area Chair of 3DV 2025, see you in Singapore.
[2024/05/08] We will organize the workshop of Foundation Models for 3D Humans on ECCV'24, call for posters and demos!
[2024/04/12] BOFT (ICLR'24) has been integrated into
[2024/03/21] I will serve as the Publicity Chair of 3DV (2025), please share your academic meme via @3DVconf
[2024/01/31] My three master mentees got their Ph.D. offers from TUM , MBZUAI, and HKU, see my Mentoring List.
[2024/01/16] G-Shell and BOFT get accepted by ICLR 2024, and G-Shell is selected as Oral (top 1.2%).
[2023/12/14] I will join Westlake University as a tenure-track Assistant Professor in Spring 2025, and relocate to Hangzhou.

---

[2023/11/13] "Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization" comes out, see BOFT.
[2023/11/09] Invited talk "Democratizing Human Digitization" at Westlake University [ Slides]
[2023/10/24] "Ghost on the Shell: An Expressive Representation of General 3D Shapes" comes out, see G-Shell.
[2023/10/16] Both TeCH and TADA get accepted by 3DV 2024.
[2023/08-09] Invited talks "Human Digitization from Pixels and Tokens" at Google Research, Cornell, Tsinghua IIIS, and IDEA
[2023/08/21] "TADA! Text to Animatable Digital Avatars" comes out, see TADA.
[2023/08/17] "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans" comes out, see TeCH.
[2023/07/14] "D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field" (ICCV 2023), see D-IF.
[2023/01-06] Invited  Talk (30 min) "Towards Large-scale Human Digitization: Implicit or Explicit?" ( Slides, 75MB) at industry (Taichi, Shanghai AI Lab, BIGAI, Huawei) and academia (PKU, CUHK, UCLA, ETH Zurich, SDU, CAS).
[2023/04/23] ECON won Outstanding Poster (4/80) in China 3DV.
[2023/04/16] Now both and are available for ECON users!
[2023/03/21] ECON has been selected as CVPR highlight papers (10% of accepted papers, 2.5% of submissions).
[2023/03/15] 💕 I'm thrilled to announce that Cathy and I are finally tying the knot! 💍 Love Moment
[2023/02/27] ECON and CAR got accepted by CVPR 2023. Byebye Vancouver!
[2023/02/13] NYTimes"See How Kansas City Secured Its Comeback", ICON for Super Bowl 2023!
[2023/01/12] Multiple contributors support Windows, Docker, Blender andGoogle Colab for ECON, bravo!
[2022/12/20] NYTimes"Modeling Key World Cup Moments with Machine Learning", ICON for World Cup 2022!
[2022/12/15] ICON belongs to the past, ECON is the future!
[2022/11/07] AlphaPose finally got accepted by TPAMI 2022
[2022/09/17] DART got accepted by NeurIPS 2022 - Datasets and Benchmarks Track.
[2022/08/29] I am invited to give a talk at Adobe's Digital Human Seminar.
[2022/08/01] of ICON, play with it on your images!
[2022/04/20] Invited to talk about ICON at Talking Papers Podcast. Great chat with Yizhak Ben-Shabat!
[2022/04/07] 走进马克思普朗克智能系统研究所与苏黎世联邦理工AIT团队  视频(中文) [上, 下].
[2022/03/02] ICON got accepted by CVPR 2022 →  Reader  Discord 
[2022/02/01] I am invited to give Tech Talks by USC-ICT, and Meta Reality Labs, Pittsburgh (PDF, 21MB).
[2021/12/17] New work "ICON: Implicit Clothed humans Obtained from Normals", please check its page.
[2020/09/01] Get admitted to CLIPE ESR11 and will be joining Michael Black's team at MPI for Intelligent Systems.
[2020/08/26] " Volumetric Human Teleportation" won Best in Show Award of SIGGRAPH Real-Time Live 2020!
[2020/08/25] Project-Splinter: Human Digitization with Implicit Representation is launched!
[2020/07/02] Our "Monoport: Monocular Real-Time Volumetric Teleportation" work was accepted by ECCV 2020
[2020/05/08] Our "Volumetric Human Teleportation" demo was accepted by SIGGRAPH Real-Time Live 2020
[2019/03/03] I will be joining USC CS Ph.D. Program in fall 2019, advised by Hao Li
[2019/01/24] I gave an invited talk at MPI for Intelligent Systems, Perceiving Systems department.

Publications

	PuzzleAvatar: Assembling 3D Avatars from Personal Albums  Yuliang Xiu, Yufei Ye, Zhen Liu, Dimitrios Tzionas, Michael J. Black ACM Transactions On Graphics (SIGGRAPH Asia), 2024  Intro   Home   Paper  Video   Bibtex
	StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal  Chongjie Ye*, Lingteng Qiu*, Xiaodong Gu, Qi Zuo, Yushuang Wu, Zilong Dong, Leifeng Bo, Yuliang Xiu#, Xiaoguang Han# (* equal contribution, # corresponding author) ACM Transactions On Graphics (SIGGRAPH Asia), 2024  Intro   Home   Paper  Video   Bibtex
	Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization  Weiyang Liu*, Zeju Qiu*, Yao Feng†, Yuliang Xiu†, Yuxuan Xue†, Longhui Yu†, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf (*/† equal contribution) International Conference on Learning Representations (ICLR 2024)  Intro   Home   Paper  Bibtex
	Ghost on the Shell: An Expressive Representation of General 3D Shapes  Zhen Liu, Yao Feng†, Yuliang Xiu†, Weiyang Liu, Liam Paull, Michael J. Black, Bernhard Schölkopf († equal contribution) International Conference on Learning Representations (ICLR 2024, Oral)  Intro   Home   Paper  Bibtex
	TeCH: Text-guided Reconstruction of Lifelike Clothed Humans  Yangyi Huang*, Yuliang Xiu*, Hongwei Yi*, Tingting Liao, Jiaxiang Tang, Deng Cai, Justus Thies (*equal contribution) International Conference on 3D Vision 2024 (3DV 2024)  Intro   Home   Video  Paper  Bibtex
	TADA! Text to Animatable Digital Avatars  Tingting Liao*, Hongwei Yi*, Yuliang Xiu, Jiaxiang Tang, Yangyi Huang, Justus Thies, Michael J. Black (*equal contribution) International Conference on 3D Vision 2024 (3DV 2024)  Intro   Home   Paper  Video  Bibtex
	D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field  Xueting Yang*, Yihao Luo*, Yuliang Xiu, Wei Wang, Hao Xu, Zhaoxin Fan (*equal contribution) International Conference on Computer Vision 2023 (ICCV 2023)  Intro   Home   Paper  Bibtex
	ECON: Explicit Clothed humans Optimized via Normal integration  Yuliang Xiu, Jinlong Yang, Xu Cao, Dimitrios Tzionas, Michael J. Black Computer Vision and Pattern Recognition 2023 (CVPR 2023, Highlight)  Intro   Home   Paper  Video   Zhihu   Bibtex
	High-Fidelity Clothed Avatar Reconstruction from a Single Image   Tingting Liao, Xiaomei Zhang, Yuliang Xiu, Hongwei Yi, ..., Xiangyu Zhu, Zhen Lei Computer Vision and Pattern Recognition 2023 (CVPR 2023)  Intro   Home   Paper  Bibtex
	AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time  Hao-shu Fang*, Jiefeng Li*, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-lu Li, Cewu Lu (*equal contribution) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2022)  Intro   Home   Paper  Video   Bibtex
	DART: Articulated Hand Model with Diverse Accessories and Rich Textures  Daiheng Gao*, Yuliang Xiu*, Kailin Li*, Lixin Yang*,..., Cewu Lu, Ping Tan (*equal contribution) Neural Information Processing Systems (NeurIPS 2022 -Datasets and Benchmarks Track)  Intro   Home   Paper  Video   Bibtex
	ICON: Implicit Clothed humans Obtained from Normals  Yuliang Xiu, Jinlong Yang, Dimitrios Tzionas, Michael J. Black Computer Vision and Pattern Recognition 2022 (CVPR 2022)  Intro   Home   Paper  Slides   Video   Zhihu   Bibtex
	Monocular Real-Time Volumetric Performance Capture  Ruilong Li*, Yuliang Xiu*, Shunsuke Saito, Zeng Huang, Kyle Olszewski, Hao Li (*equal contribution) European Conference on Computer Vision (ECCV 2020)  Intro   Home   Paper  Video   Zhihu   Bibtex
	Volumetric Human Teleportation  Ruilong Li, Kyle Olszewski, Yuliang Xiu, Shunsuke Saito, Zeng Huang, Hao Li SIGGRAPH Real-Time Live 2020 (Best in Show Award)  Intro   Home   Paper  Video   Bibtex
	Pose Flow: Efficient Online Pose Tracking  Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, Cewu Lu British Machine Vision Conference (BMVC 2018)  Intro   Paper  Zhihu   Bibtex

Endless AI @ Westlake

• Research Assistants
• Xingyu Chen, Xi'an Jiao Tong University, co-advised with Anpei Chen
• Yue Chen, Xi'an Jiao Tong University, co-advised with Gerard Pons-Moll
• Xiaoben Li, ShanghaiTech University, co-advised with Jingbo Wang
• Jiaxin Wang, Hangzhou Dianzi University, co-advised with Anpei Chen
• Long Wang, Zhejiang University, co-advised with Tim Z. Xiao
• Longhui Yu, Peking University, co-advised with Weiyang Liu and Kaicheng Yu
• Visiting Students
• Zeyu Cai, Hong Kong University of Science and Technology (Guang Zhou), co-advised with Zhen Liu
• He Guo, Huazhong University of Science and Technology, co-advised with Weiyang Liu and Yandong Wen
• Boqian Li, Huazhong University of Science and Technology, co-advised with Haven Feng
• Congrong Xu, ShanghaiTech University, co-advised with Anpei Chen
• External Collaborators
• Siyuan Bian, Shanghai Jiao Tong University, co-advised with Yao Feng
• Tingting Liao, Mohamed bin Zayed University of Artificial Intelligence, co-advised with Hao Li
• Jingyi Wu, Fudan University

Mentoring @ MPI-IS

• Yangyi Huang (2023-Now): TeCH (3DV'24)
  • Master at Zhejiang University
  • → Ph.D. at Technical University of Munich (TUM), advised by Angela Dai
• Tingting Liao (2022-Now) : CAR (CVPR'23), TADA (3DV'24)
  • Master at Chinese Academy of Sciences
  • → Ph.D. at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), advised by Hao Li
• Xueting Yang (2023-Now) : D-IF (ICCV'23)
  • Undergrad at Communication University of China
  • → Ph.D. at The University of Hong Kong (HKU), advised by Kenneth K.Y. Wong
• Daiheng Gao (2022-Now) : DART (NeurIPS'22)
  • Senior algorithm engineer in XR Lab at Alibaba

Invited Talks

• PuzzleAvatar: Assembling 3D Avatars from Personal Albums [ Slides (215MB)]
CMU, Tsinghua, GAMES
• Carnegie Mellon Graphics Lab, hosted by Minchen Li
• GAMES Webinar, hosted by Yichao Yan
• Tsinghua University, Institute for Al Industry Research (AIR), hosted by Hao Zhao
• Democratizing Human Digitization [ Slides (122MB)]
TAMU, Westlake, ZJU, JHU
• Texas A&M University, Guest Lecture at CSCE 689 Special Topics: Generative AI, hosted by Zhengzhong Tu
• Westlake University, hosted by Xiaofei Li
• Zhejiang University, hosted by Tianyu Du
• Johns Hopkins University, hosted by Zongwei Zhou and Yaoyao Liu
• Human Digitization from Pixels and Tokens
Google Research, Cornell, Tsinghua, IDEA
• Google Research, hosted by Thiemo Alldieck
• Cornell University, hosted by Ruolin Ye
• Tsinghua University, Institute for Interdisciplinary Information Sciences (IIIS), hosted by Li Yi
• International Digital Economy Academy (IDEA), Computer Vision and Robotics, hosted by Ailing Zeng
• Towards Large-scale Human Digitization: Implicit or Explicit? [ Slides (75MB),  Video (30 min)]
  Taichi, PKU, CUHK, UCLA, ETH Zurich, SDU, CAS, Shanghai AI Lab, BIGAI, Huawei

  • Taichi Graphics(太极大讲堂), hosted by Tiantian Liu and Qing Yan
  • Huawei (CG&XR武林大会), hosted by Shiqi Zhou
  • Huawei (稼先社区&藤蔓技术论坛), hosted by Tao Bai
  • ETH Zurich, Photogrammetry and Remote Sensing Lab, hosted by Shengyu Huang
  • BIGAI, Beijing Institute for General Artifical Intelligence, hosted by Yixin Chen
  • Shanghai AI Laboratory, Content Generation and Digitization Group, hosted by Bo Dai
  • UCLA, Multi-Physics Lagrangian-Eulerian Simulations (MultiPLES) Laboratory, hosted by Ziyin Qu
  • Shandong University, Interdisciplinary Research Center & Taishan College, hosted by Haisen Zhao
  • Shandong University, Research Center of Human-Computer Interaction and Virtual Reality, hosted by Lu Wang
  • CUHK, The Chinese University of Hong Kong (Shenzhen), GAP Lab, hosted by Xiaoguang Han
  • ICT CAS, Institute of Computing Technology, Chinese Academy of Sciences, hosted by Lin Gao and Jie Yang
  • Peking University, the School of Artificial Intelligence, hosted by Siyan Dong and Baoquan Chen
• 如何多快好省地重建三维数字人 [ TechBeat (40 min)]
• 走进马克思普朗克智能系统研究所与苏黎世联邦理工AIT团队 [  Part A (2h),  Part B (2h)]
• ICON: 提高三维数字人重建的姿势水平 [ Keynote (726MB),  Video (60 min)]
• Talking Papers Podcast: ICON [Link]
• Towards Large-scale Avatar Creation From In-the-wild Pixels [ Slides, 25MB]
  Meta, USC, OPPO, Tecent, Adobe

  • Meta Reality Labs, Pittsburgh, hosted by Shunsuke Saito and Giljoo Nam
  • USC-ICT, USC Institute for Creative Technology, hosted by Yajie Zhao
  • Adobe, Digital Humans Seminar, hosted by Yi Zhou
  • OPPO, US Research Center, hosted by Xudong Liu and Guojun Qi
  • Tecent, GY-Lab(光影研究室), hosted by Chao Xu and Gang Yu
• Pose trajectory extraction and novel-view synthesis from visual content [Link]
  • Max Planck Institute for Intelligent Systems, hosted by Siyu Tang

Academic Service

• Computer Graphics (CG):
  • Conference Reviewer: SIGGRAPH (2022, 2023), SIGGRAPH Asia (2023, 2024), Eurographics (2024)
  • Journal Reviewer: TVCG, TOG
• Computer Vision (CV):
  • Conference Reviewer: CVPR (2022, 2023, 2024), ECCV (2022, 2024), ICCV (2023), NeurIPS (2023), 3DV (2024)
  • Journal Reviewer: T-PAMI, TIP
  • Area Chair: 3DV (2025)
  • Publicity Chair: 3DV (2025)
  • Workshop Organizer:
  • Foundation Models for 3D Humans (ECCV'24)

Blogs & Medias

• Blog CVPR'23 (Highlight) | ECON: 一个数字人，显式隐式各自表述  
• Blog CVPR 2022 | ICON: 提高三维数字人重建的姿势水平  
• Translation 当我们谈科学研究的创新性时，我们在谈些什么  Source   译文 
• NYTimes"See How Kansas City Secured Its Comeback", ICON for Super Bowl 2023
• NYTimes "Modeling Key World Cup Moments with Machine Learning", ICON for World Cup 2022
• ACMSIGGRAPH "Broadcast From Around the World", MonoPort wins SIGGRAPH 2020 Real-Time Live