Sizhuo Ma

Research Scientist, Snap Research

I am a Senior Research Scientist at Snap Research. My current research focuses on high-fidelity image & video restoration and enhancement, and efficient vision-language models. Please check my Google Scholar page for a complete list of publications.

I received my PhD in Computer Sciences at UW-Madison, advised by Professor Mohit Gupta. My PhD work focused on solving geometry and motion-related computer vision problems using novel computational cameras, including light field cameras, structured light, and single-photon cameras.

Portrait of Sizhuo Ma

Research

Guohao Sun, Yufei Wang, Sizhuo Ma, Yuege Xie, Yuting Cheng, Zhiqiang Tao, Jian Wang

IF-Prune: Information-Flow Guided Token Pruning for Efficient Vision-Language Models

CVPR 2026

Velocity Disambiguation thumbnail

Zhihang Zhong, Gurunandan Krishnan, Wei Wang, Xiao Sun, Yu Qiao, Sizhuo Ma*, Jian Wang*

Velocity Disambiguation for Video Frame Interpolation

TPAMI 2026

Ayush Garg, Sizhuo Ma, Mohit Gupta

gQIR: Generative Quanta Image Reconstruction

CVPR 2026

Eric Ming Chen, Di Liu, Sizhuo Ma, Michael Vasilkovsky, Bing Zhou, Qiang Gao, Wenzhou Wang, Jiahao Luo, Dimitris N. Metaxas, Vincent Sitzmann, Jian Wang

Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars

WACV 2026

PDF / Project

Jiahao Guo, Yifan Ji, Zhenzhong Chen, Yufei Wang, Sizhuo Ma, Yuwei Guo, Yulun Zhang, Jian Wang

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

arXiv, 2025

Sizhuo Ma, Wei-Ting Chen, Qiang Gao, Jian Wang, Chris Wei Zhou, Wei Sun, Weixia Zhang, Linhan Cao, et al.

VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

ICCV Workshop 2025

PDF / Challenge / Workshop

Dasong Li*, Sizhuo Ma*, Hang Hua*, Wenjie Li*, Jian Wang*, Chris Wei Zhou*, Fengbin Guan, Xin Li, et al.

VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results

ICCV Workshop 2025

PDF / Challenge / Workshop

Sizhuo Ma, Karl Bayer, Gurunandan Krishnan, Mohit Gupta, Shree Nayar

Privacy-Enabled Parallax Display

IEEE VR 2025

Howard Zhang+, Yuval Alaluf+, Sizhuo Ma, Achuta Kadambi, Jian Wang*, Kfir Aberman*

InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention

SIGGRAPH 2025

PDF / Project / Video / Code

Privacy-preserving event localization thumbnail

Junho Kim, Young Min Kim, Ramzi Zahreddine, Weston A. Welge, Gurunandan Krishnan, Sizhuo Ma*, Jian Wang*

Privacy-Preserving Visual Localization with Event Cameras

TIP 2025

PDF / Project / Code / Video

Yiming Zhang, Lionel Zhe Wang+, Sizhuo Ma+, Xinjie Li, Jian Ren, Zhihang Zhong*, Jian Wang*

DiffBody: Human Body Image Restoration with Generative Diffusion Prior

ICCP 2025

PDF / Code

Aditya Arora, Zhengzhong Tu+, Yufei Wang+, Ruizheng Bai, Jian Wang*, Sizhuo Ma*

GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution

arXiv, 2025

PDF

Wei-Ting Chen+, Vong Yu Jiet+, Yi-Tsung Lee, Qiang Gao, Sy-Yen Kuo, Sizhuo Ma*, Jian Wang*

DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor

arXiv, 2025

PDF

Jian Wang, Sizhuo Ma, Karl Bayer, Yi Zhang, Peihao Wang, Bing Zhou, Shree Nayar, Gurunandan Krishnan

Perspective-Aligned AR Mirror with Under-Display Camera

SIGGRAPH Asia 2024, Best Paper Award

PDF / Supp / Video

Dasong Li, Wenjie Li, Baili Lu, Hongsheng Li, Sizhuo Ma, Gurunandan Krishnan, Jian Wang

Delving Deep into Engagement Prediction of Short Videos

ECCV 2024

PDF / Supp / Code and data

Dorian Chan, Matthew O'Toole, Sizhuo Ma, Jian Wang

Holodepth: Programmable Depth-Varying Projection via Computer-Generated Holography

ECCV 2024

PDF / Supp / Code