Peizhuo Li

Peizhuo Li

Machine Learning Engineer

Apple

Short Bio

My name is Peizhuo Li (李沛卓). I am a Machine Learning Engineer at Apple. I received my PhD from the Interactive Geometry Lab, ETH Zurich, under the supervision of Prof. Olga Sorkine-Hornung. My research lies at the intersection of deep learning and computer graphics, with an emphasis on modeling, control, and generative models for character animation, as well as related problems in geometry and physics. Prior to my PhD study, I was a student researcher at the Visual Computing and Learning lab at Peking University and advised by Prof. Baoquan Chen.

Interests

  • Computer Graphics
  • Character Animation
  • Deep Learning

Education

  • Direct Doctorate, 2021 ~ 2026

    ETH Zurich

  • BSc in Computer Science, 2017 ~ 2021

    Turing Class, Peking University

Recent Publications

Gradient Descent in the ALPS: Abstracted Low-Poly Stylization and Fabrication

Low-poly vector art represents an image with a small set of flat-shaded polygons and a limited color palette, making results easy to …
SIGGRAPH 2026
Project page Paper Supplementary Overview video Code

MotionPyramid: Controllable Motion Synthesis via Stylized Phase Manifolds

We introduce stylized phase manifolds, a compact, interpretable latent representation that disentangles motion content (e.g., …
Computer Graphics Forum (Proceedings of SCA 2026)
Project page Paper Code

Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs

Ballroom dancing is a structured yet expressive motion category. Its highly diverse movement and complex interactions between leader …
Arxiv 2026
Website Paper Supplemental

Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior

We introduce a neural motion synthesis approach that uses accessible pose data to generate plausible character motions by transferring …
Symposium on Computer Animation (SCA) 2024, Computer Graphics Forum
Website Paper Supplemental Code

WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds

We introduce a novel approach to learn a common phase manifold from motion datasets across different characters, such as human and dog, …
SIGGRAPH 2024, Technical Papers Track
Website Paper Supplemental Code

Neural Garment Dynamics via Manifold-Aware Transformers

Data driven and learning based solutions for modeling dynamic garments have significantly advanced, especially in the context of …
Eurographics 2024, Computer Graphics Forum
Website Paper Supplemental Code

Example-based Motion Synthesis via Generative Motion Matching

We present Generative Motion Matching (GenMM), a generative model that “mines” as many diverse motions as possible from a …
SIGGRAPH 2023, ACM Transactions on Graphics (TOG)
Website Live demo Paper Supplemental Code

MoDi: Unconditional Motion Synthesis from Diverse Data

The emergence of neural networks revolutionized motion synthesis, yet synthesizing diverse motions remains challenging. We present …
CVPR 2023
Website Paper Supplemental Code

GANimator: Neural Motion Synthesis from a Single Sequence

We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence. GANimator …
SIGGRAPH 2022, ACM Transactions on Graphics (TOG)
Website Paper Supplemental Code

Learning Skeletal Articulations with Neural Blend Shapes

We develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure, which is essential …
SIGGRAPH 2021, ACM Transactions on Graphics (TOG)
Website Paper Supplemental Code

Skeleton-Aware Networks for Deep Motion Retargeting

We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, …
SIGGRAPH 2020, ACM Transactions on Graphics (TOG)
Website Paper Supplemental Code