Objects as Audio-Visual Modal Sound Fields
Reconstructing how objects sound from multi-view images and a few impact recordings.
Hi, I’m Zihao Wei.
I am a second-year Ph.D. student in Computer Science at the University of Maryland, College Park, where I work as a research assistant under the supervision of Prof. Ruohan Gao. Prior to this, I completed my master’s studies under the guidance of Prof. Andrew Owens at University of Michigan, Ann Arbor. I have also had the opportunity to collaborate with Prof. Cihang Xie, Prof. Yuyin Zhou, and Prof. Alan Yuille during a summer research internship at Johns Hopkins University and the University of California, Santa Cruz. During my undergraduate studies, I worked with Prof. Chengbin Ma at Shanghai Jiao Tong University.
If you are interested in learning more about me, I would love to chat and explore potential collaboration opportunities. Please email me at - [email protected]
News and Updates
- Jun 2026： One co-first author paper is accepted by ECCV 2026.
- Apr 2026： Join JSALT workshop at JHU.
- Aug 2025： One paper is accepted by EMNLP 2025.
- Mar 2025： Will join UMD as a PhD student.
- Apr 2024： One first author paper is accepted by the Efficient Deep Learning for Computer Vision Workshop 2024 at CVPR.
- Feb 2024： Two co-first author papers are accepted by CVPR 2024.
- Aug 2023： One first author paper is accepted by PRICAI 2023.
- Jun 2023： One co-first author paper is accepted as oral by MICCAI 2023.
RESEARCH
Selected publications
* denotes equal contribution. Click a figure to explore the method.
Masked Diffusion Captioning for Visual Feature Learning
Learning visual representations by reconstructing masked captions with an image-conditioned diffusion model.
Masked Autoencoders are Secretly Efficient Learners
A lighter pre-training recipe unlocks the time and sample efficiency of masked autoencoders.
Efficient Vision-Language Pre-training by Cluster Masking
Masking clusters of visually similar patches for efficient vision-language representation learning.
MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections
Combining implicit representations and diffusion to recover 3D structure from limited microscopy projections.
A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators
Attention U-Net discriminators for sharper real-world blind super-resolution.
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
Multi-view masked learning with Swin Transformers for 3D medical image segmentation.
Technical report
Bridging Audio-Visual Semantics with Language-Guided Synthesis
Language-guided cross-modal synthesis for audio-visual representation learning.
Academic Background
- Sep 2025 - Present: University of Maryland, College Park (Ph.D, Computer Science)
- Aug 2023 - Apr 2025: University of Michigan (MS, Computer Science)
- May 2022 - Oct 2023: University of California, Santa Cruz (Research Intern)
- Summer 2022: Johns Hopkins University (Research Intern)
- Aug 2021 - Apr 2023: University of Michigan (BSE, Computer Science)
- Sep 2019 - Aug 2023: Shanghai Jiao Tong University (BSE, Electrical and Computer Engineering)
Competitions
- May 2021：Third Prize in 11-th Innovation, Creativity and Entrepreneurship Comptetition
- Feb 2021：Finalist Award in Mathematical Contest In Modeling (Top 1%)
- Dec 2020：The Excellence Awards in World Robot Competition Finalsan and Smart Robot Expo (Top 1)
- Dec 2019：Best Design Awards in China trails for 2019 VEX World Companships
Honors
- Summa Cum Laude — Aug 2023
- Dean’s List — Apr 2023, Dec 2022, Apr 2022, Dec 2021
- University Honors — Dec 2022, Apr 2022, Dec 2021
- Academic Excellent Scholarship — Aug 2020
Services
- Reviewer: TPAMI, CVPR, ICCV, ECCV, ICLR, NeurIPS, AAAI, WACV, UIST
Teaching
- CMSC 848M: Multimodal Computer Vision, Spring 2026
- CMSC 498K: Introduction to Multimodal Deep Learning, Fall 2025
- EECS 376: Foundations of Computer Science, Winter 2022