Hi, I’m Shizun Wang, currently a first-year Ph.D. student at the amazing LV Lab @ NUS, supervised by Prof. Xinchao Wang. Before joining LV Lab, I completed my B.E. and M.S. degrees at Beijing University of Posts and Telecommunications, where I worked at the PRIS Lab under the supervision of Prof. Chuang Zhang.

My research focuses on Computer Vision, with a particular interest in learning-based visual content (image/video/3D) synthesis (generation/editing/animating) from multi-modality inputs (text/brain signals).

Publications

• GFlow: Recovering 4D World from Monocular Video
  Shizun Wang, Xingyi Yang, Qiuhong Shen, Zhenxiang Jiang, Xinchao Wang
  Arxiv Preprint, 2024
  [Paper] [Project]

• MindBridge: A Cross-Subject Brain Decoding Framework
  Shizun Wang, Songhua Liu, Zhenxiong Tan, Xinchao Wang
  Computer Vision and Pattern Recognition Conference (CVPR), 2024 (Highlight)
  [Paper] [Project] [Code]

• PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
  Li Chen, Mengyi Zhao, Yiheng Liu, Mingxu Ding, Yangyang Song, Shizun Wang, Xu Wang, Hao Yang, Jing Liu, Kang Du, Min Zheng
  Arxiv Preprint, 2023
  [Paper] [Project]

• SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
  Shizun Wang, Weihong Zeng, Xu Wang, Hao Yang, Li Chen, Yi Yuan, Yunzhao Zeng, Min Zheng, Chuang Zhang, Ming Wu
  AAAI Conference on Artificial Intelligence (AAAI), 2023 (Oral)
  [Paper]

• Adaptive Patch Exiting for Scalable Single Image Super-Resolution
  Shizun Wang, Jiaming Liu, Kaixin Chen, Xiaoqi Li, Ming Lu, Yandong Guo
  European Conference on Computer Vision (ECCV), 2022 (Oral)
  [Paper] [Code]

• Efficient Meta-Tuning for Content-aware Neural Video Delivery
  Xiaoqi Li, Jiaming Liu, Shizun Wang, Cheng Lyu, Ming Lu, Yurong Chen, Anbang Yao, Yandong Guo, Shanghang Zhang
  European Conference on Computer Vision (ECCV), 2022
  [Paper] [Code]

• SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution
  Shizun Wang, Ming Lu, Kaixin Chen, Jiaming Liu, Xiaoqi Li, Ming Wu
  The British Machine Vision Conference (BMVC), 2021
  [Paper] [Code]

• Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
  Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu
  International Conference on Computer Vision (ICCV), 2021
  [Paper] [Code]

Internship

• Intel labs China
  • 3D Human Motion Capture (Transfer to 3D Athlete Tracking)
  • Image Restoration (Super-resolution, Denoising)
  • Neural Video Delivery
• SenseTime
  • Deep Image Compression
  • Image Coding for Machine
• OPPO Research Institute
  • Dynamic neural network
  • Learn-based Visual Synthesis
• ByteDance
  • Generative models
  • Avatars
  • AIGC

Education

• National University of Singapore, Singapore (Aug. 2023 - Now)
  • Ph.D., Electrical & Computer Engineering
  • Supervisor: Xinchao Wang
• Beijing University of Posts and Telecommunications, China (Sep. 2020 - Jun. 2023)
  • M.S., Information & Communication Engineering
  • Supervisor: Chuang Zhang
• Beijing University of Posts and Telecommunications, China (Sep. 2016 - Jun. 2020)
  • B.E., Internet of Things Engineering
  • Joint programme with Queen Mary University of London

Services

Reviewer for CVPR, NeurIPS, ECCV, ICCV, AAAI, TIP.