Yuxuan Mu (Matthew)

Currently a Ph.D. student at GrUVi Lab, Simon Fraser University, working on 3D computer vision and animation. I primarily focus on 3D character motion modeling advised by Professor Xue bin (Jason) Peng.

I obtained my master’s degree at University of Alberta advised by Professor Li Cheng. I've worked as a research intern at Huawei Canada (Noah’s Ark Lab) on 3D generation and reconstruction with Juwei Lu and Xinxin Zuo.

Email  /  GitHub  /  LinkedIn  /  X

profile photo

Research

My work involves 3D human motion estimation, generation, physics simulation, and rendering. The goal is to bridge the gap between physical and virtual reality, fostering enhanced mutual perception, understanding, and interaction. Specifically, I design generative models and reinforcement learning systems that use physics simulations to better model human behavior and interactions.

'*' indicates equal contribution.

project image

MotionDreamer: One-to-More Motion Synthesis with Localized Generative Masked Transformer


Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Li Cheng, Hai Jiang, Juwei Lu
ICLR, 2025
webpage / paper /

Localized masked modeling paradigm to learn motion internal patterns from one motion with arbitrary topology.

project image

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction


Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofei Wu, Songcen Xu, Peng Dai, Youliang Yan, Li Cheng
ECCV, 2024
webpage / paper /

The first 3D diffusion model directly upon Gaussian Splatting for real‐world object reconstruction, with fine-grained view-guided conditioning.

project image

MoMask: Generative Masked Modeling of 3D Human Motions


Chuan Guo*, Yuxuan Mu*, Muhammad Gohar Javed*, Sen Wang, Li Cheng
CVPR, 2024
webpage / paper / code / demo / Star

We introduce MoMask, a novel masked modeling frame work for text‐driven 3D human motion generation with a hierarchical quantization scheme.

project image

Generative Human Motion Stylization in Latent Space


Chuan Guo*, Yuxuan Mu*, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng
ICLR, 2024
webpage / paper / code /

We propose a flexible motion style extraction and injection method from a generative perspective to solve the motion stylization task with probabilistic style space.

project image

RACon: Retrieval-Augmented Simulated Character Locomotion Control


Yuxuan Mu, Shihao Zou, Kangning Yin, Zheng Tian, Li Cheng, Weinan Zhang, Jun Wang
ICME (Oral), 2024
paper /

We introduce an end-to-end hierarchical reinforcement learning method utilizes a task-oriented learnable retriever, a motion controller and a retrieval-augmented discriminator.

project image

Event‐based Human Pose Tracking by Spiking Spatiotemporal Transformer


Shihao Zou, Yuxuan Mu, Xinxin Zuo, Sen Wang, Li Cheng
Arxiv Preprint, 2023
paper / code /

Our SNNs approach uses at most 19.1% of the computation and 3.6% of the energy costs consumed by the existing methods while achieves superior performance.





Design and source code from Leonid Keselman's website