Zhongshi Jiang

Zhongshi Jiang

Staff Research Scientist, Reality Labs at Meta

Meta - Reality Labs

NYU Courant (Ph.D. 2022)

About Me

I am a Research Scientist at Meta Human AI, working on the next generation of human-centric communication.

I finished my Ph.D. degree at New York University, working on computer graphics and geometry processing. My PhD research aims to provide robust discrete geometry processing tools for machine learning, digital fabrication and scientific computing. My research has been recognized by Adobe Research Fellowship 2018, Geometry Processing Dataset Award 2019, and Jacob T. Schwartz PhD Fellowship 2020.

I earned my Bachelor of Science in Mathematics and Applied Mathematics from the School of Gifted Young, University of Science and Technology of China in 2016.

Email: zhongshi@cims.nyu.edu
Download my Resume

Interests
  • Digital Humans
  • Geometric Modeling
  • Geometric Computing
  • Robust Simulation
Education

  • Ph.D. in Computer Science — Dissertation: Synergistic Geometry Processing: from Robust Shape Modeling to Scalable Physical Simulation — Advisor: Prof. Daniele Panozzo, 2022 (Sep 2022, Honors: Adobe Research Fellowship 2018, Geometry Processing Dataset Award 2019)

    New York University, Courant Institute

  • B.Sc. in Mathematics and Applied Mathematics — School of Gifted Young, 2016 (Jun 2016)

    University of Science and Technology of China

Research

HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning
SIGGRAPH Asia 2026
HyperBones — realtime neural garment simulation conditioned via hypernetworks. SIGGRAPH Asia 2026.
Astitva Srivastava , Hsiao-Yu Chen , Ryan Goldade , Philipp Herholz , Zhongshi Jiang , Gene Wei-Chin Lin , Lingchen Yang , Nikolaos Sarafianos , Tuur Stuyck , Doug Roble , Avinash Sharma , Egor Larionov
PDF Project
HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
CVPR 2026
Large-Scale Codec Avatars (LCA) — high-fidelity full-body 3D avatars that generalize via pretraining on 1M in-the-wild videos then post-training on curated studio data. Meta Reality Labs / Human AI. CVPR 2026.
Junxuan Li , Rawal Khirodkar , Chengan He , Zhongshi Jiang , et al.
PDF Code Project
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
PhySkin: Physics-based Bone-driven Neural Garment Simulation
CVPR 2026
PhySkin — physics-based bone-driven neural garment simulation. Meta Reality Labs human clothing work. CVPR 2026.
Astitva Srivastava , Hsiao-Yu Chen , Ryan Goldade , Philipp Herholz , Zhongshi Jiang , Gene Wei-Chin Lin , Lingchen Yang , Nikolaos Sarafianos , Tuur Stuyck , Egor Larionov
PDF Code Project
PhySkin: Physics-based Bone-driven Neural Garment Simulation
MHR: Momentum Human Rig
arXiv:2511.15586, 2025
MHR — Momentum Human Rig, collaborative Meta effort on human rigging.
PDF Code Project
MHR: Momentum Human Rig
FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images
CVPR 2025
FRESA — feedforward personalized skinned avatar reconstruction from few images. CVPR 2025.
Rong Wang , Fabian Prada , Ziyan Wang , Zhongshi Jiang , Chengxiang Yin , Junxuan Li , Shunsuke Saito , Igor Santesteban , Javier Romero , Rohan Joshi , Hongdong Li , Jason M. Saragih , Yaser Sheikh
PDF Code Project
FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images
FaceMap: Distortion-Driven Perceptual Facial Saliency Maps
SIGGRAPH Asia 2024
FaceMap — perceptual facial saliency maps driven by visual distortion, for better avatar faces. Learned from 45+ participants pairwise study, SROCC 0.82.
Zhongshi Jiang , Kishore Venkateshan , Giljoo Nam , Meixu Chen , Romain Bachy , Jean-Charles Bazin , Alexandre Chapiro
PDF Project
FaceMap: Distortion-Driven Perceptual Facial Saliency Maps
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
ECCV 2024
RCAD — retrieval from counterfactually augmented data to test video-text models, with Feint6K dataset.
Wufei Ma , Kai Li , Zhongshi Jiang , Moustafa Meshry , Qihao Liu , Huiyu Wang , Christian Häne , Alan L. Yuille
PDF Code Dataset Project
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
Declarative Specification for Unstructured Mesh Editing Algorithms
ACM Trans. on Graphics (Proc. SIGGRAPH Asia 2022), 41(6), Article 251
A declarative spec for unstructured mesh editing: we show a system that lets you describe mesh editing algorithms at high level while the runtime handles concurrency and robustness. Presented at SIGGRAPH Asia 2022.
Zhongshi Jiang , Jiacheng Dai , Yixin Hu , Yunfan Zhou , Jérémie Dumas , Qingnan Zhou , Gurkirat Singh Bajwa , Denis Zorin , Daniele Panozzo , Teseo Schneider
PDF Code
Declarative Specification for Unstructured Mesh Editing Algorithms
Bijective and Coarse High-Order Tetrahedral Meshes
ACM Trans. on Graphics, 2021
Coarse yet accurate geometry with high order elements. We introduce a robust and automatic approach to convert triangle meshes to coarse high-order tetmeshes. We bound geometric error, ensure valid elements, and preserve features precisely. We can also transfer attributes and solutions between input and output boundary.
Zhongshi Jiang , Ziyi Zhang , Yixin Hu , Teseo Schneider , Denis Zorin , Daniele Panozzo
PDF Code Dataset Project Video
Bijective and Coarse High-Order Tetrahedral Meshes
Bijective Projection in a Shell
ACM Trans. on Graphics, 2020
Adjusting the common used orthogonal projection between discrete surfaces a reliable tool, by constructing a shell to restrict the domain. The bijective association between meshes in the shell provide a robust way to construct high quality computational proxy.
Zhongshi Jiang , Teseo Schneider , Denis Zorin , Daniele Panozzo
PDF Code Video
Bijective Projection in a Shell
A Low-Parametric Rhombic Microstructure Family for Irregular Lattices
ACM Trans. on Graphics, 2020
Microstructure family defined on rhombic meshes, with better approximation on (planar) irregular geometric domains. A smoother material-to-geometry map and fabricated results.
Davi Colli Tozoni , Jérémie Dumas , Zhongshi Jiang , Julian Panetta , Daniele Panozzo , Denis Zorin
PDF Code Video Supplemental
A Low-Parametric Rhombic Microstructure Family for Irregular Lattices
Progressive Embedding
ACM Trans. on Graphics, 2019
A numerically stable, and provably correct replacement for Tutte’s embedding. Avoid exponential area change and serve as a robust building block for locally injective maps with hard constraints, in quad meshing.
Hanxiao Shen , Zhongshi Jiang , Denis Zorin , Daniele Panozzo
PDF Code Dataset Project Video
Progressive Embedding
ABC: A Big CAD Model Dataset For Geometric Deep Learning
IEEE CVPR, 2019 / SGP Dataset Award, 2019
One million CAD models in B-Rep form, with rich information to learn from.
Sebastian Koch , Albert Matveev , Zhongshi Jiang , Francis Williams , Alexey Artemov , Evgeny Burnaev , Marc Alexa , Denis Zorin , Daniele Panozzo
PDF Dataset Project
ABC: A Big CAD Model Dataset For Geometric Deep Learning
Surface Networks
CVPR 2018 Oral
Dirac-based Surface Networks for meshes – extrinsic geometry for anisotropic deformation prediction (CVPR 2018 Oral, first-author Ilya Kostrikov, my fork maintained).
Ilya Kostrikov , Zhongshi Jiang , Daniele Panozzo , Denis Zorin , Joan Bruna
PDF Code
Surface Networks
Simplicial Complex Augmentation Framework for Bijective Maps
ACM Trans. on Graphics, 2017
A robust and efficient way optimize the distortion of bijective maps via scaffold augmentation – reducing global bijectivity to local injectivity. Applicable to 2D (bijective surface parameterization) and 3D (intersection-free deformation).
Zhongshi Jiang , Scott Schaefer , Daniele Panozzo
PDF Code Project Slides
Simplicial Complex Augmentation Framework for Bijective Maps

Lectures & Teaching

Lectures

External Events & Invited Talks

  • Invited lecture series on robust geometry processing and neural representations for digital humans — notes and recordings on YouTube.

  • Industry panels on photorealistic avatars and physics-aware garment simulation (Meta Reality Labs) — 2023–2026.

YouTube Channels

  • Personal / Lectures — youtube.com/@zhongshijiang — geometry processing, robust optimization, and recent SIGGRAPH / CVPR paper walkthroughs

  • Topics: Progressive Embedding, Bijective Maps, Scaffold Maps, Quadfoam microstructures, Surface Networks Dirac operator, and digital human avatar series

  • More recordings: SGP 2021 playlist above, ChinaGraph 2020 full lecture (2h)