I am a PhD student in Machine Learning supervised by Thomas Schön and co-supervised by Jens Sjölund and Fredrik K. Gustafsson at Uppsala University. My research interest generally includes Machine Learning, Computer Vision, and Reinforcement Learning. And my recent works mainly focus on Probabilistic deep learning with application in computer vision.
I received my Master of Engineering degree from the School of Computer Science, Chengdu University of Information Technology, advised by Jing Hu. During the school, I participated in the project of performing image registration via reinforcement learning, under the advising of Xin Wang and Siwei Lyu from the University at Buffalo, SUNY. Before that, I obtained the Bachelor degree from Hebei University of Technology. I had been a research assistant at Megvii Technology Ltd., China, working with Shuaicheng Liu.
🔥 News
- 2024.11: 🎉🎉 I was selected as a Top Reviewer in NeurIPS 2024.
- 2024.09: 🎉🎉 One paper is accepted by Advances in Neural Information Processing Systems (NeurIPS 2024).
- 2024.01: 🎉🎉 One paper is accepted by International Conference on Learning Representations (ICLR 2024).
- 2023.04: 🎉🎉 One paper is accepted by International Conference on Machine Learning (ICML 2023).
- 2023.04: 🎉🎉 We win 2nd place in the NTIRE 2023 Shadow Removal Challenge (1st place on perceptual scores).
- 2022.04: 🎉🎉 We win 1st place in the NTIRE 2022 Burst Super-Resolution Challenge (Real-World Track).
- 2022.03: 🎉🎉 One paper is accepted by IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022).
📝 Publications
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
Ruoqi Zhang$^\dagger$, Ziwei Luo$^\dagger$, Jens Sjölund, Thomas B. Schön, Per Mattsson
- This work presents a diffusion-based policy for offline reinforcement learning.
- A diffusion entropy and the Q-ensembles are introduced to improve the RL performance.
Controlling Vision-Language Models for Multi-Task Image Restoration
Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön
ICLR 2024 | Paper | Code | Project
- This work presents a degradation-aware vision-language model (DA-CLIP) for multi-task image restoration.
- A controller predicts degradation types and also adapts the fixed CLIP image encoder to predict high-quality feature embeddings.
Image Restoration with Mean-Reverting Stochastic Differential Equations
Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön
ICML 2023 | Paper | Code | Project
- This work presents a stochastic differential equation (SDE) approach for general-purpose image restoration.
- A maximum likelihood objective is proposed to learn an optimal reverse trajectory which stabilizes the training and improves accuracy.
Deep Constrained Least Squares for Blind Image Super-Resolution
Ziwei Luo, Haibin Huang, Lei Yu, Youwei Li, Haoqiang Fan, Shuaicheng Liu
- This work proposes to disentangle deblurring and upsampling in blind super-resolution, and provides a theoretical guidance to make use of the kernel.
Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration
Ziwei Luo*, Jing Hu*, Xin Wang, Shu Hu, Bin Kong, Youbing Yin, Qi Song, Xi Wu, Siwei Lyu
- It is the first work that performs deformable image registration via high-dimensional action deep reinforcement learning.
-
Stochastic Actor-Executor-Critic for Image-to-Image Translation
Ziwei Luo*, Jing Hu*, Xin Wang, Siwei Lyu, Bin Kong, Youbing Yin, Qi Song, Xi Wu
IJCAI 2021 | [Paper] -
End-to-end multimodal image registration via reinforcement learning
Jing Hu, Ziwei Luo, Xin Wang, Shanhui Sun, Youbing Yin, Kunlin Cao, Qi Song, Siwei Lyu, Xi Wu
Medical Image Analysis 2021 | [Paper] -
A Spatiotemporal Agent for Robust Multimodal Registration
Ziwei Luo, Xin Wang, Xi Wu, Youbing Yin, Kunlin Cao, Qi Song, Jing Hu
IEEE ACCESS 2020 | [Paper]
🎖 Honors and Awards
- 2023 2nd place in NTIRE Shadow Removal Challenge (1st place on perceptual scores)
- 2021, 2022 Champion in NTIRE Burst Super-Resolution Challenge (Real track)
- 2021 Outstanding Graduates, Chengdu University of Information Technology
- 2021 Award of Scientific Thesis Excellence, Chengdu University of Information Technology
- 2020 The First Prize Scholarship, Chengdu University of Information Technology
- 2020 National Scholarship, China
📖 Educations
- 2022.09 - present, PhD student, Uppsala University.
- 2018.09 - 2021.06, Master, Chengdu University of Information Technology.
- 2011.09 - 2015.06, Undergraduate, Hebei University of Technology.
💬 Teaching
- Teaching Assistant in the course Advanced Probabilistic Machine Learning, at Uppsala University
- Teaching Assistant in the course Statistical Machine Learning, at Uppsala University
- Teaching Assistant in the course Foundations of Computer Science, at Chengdu University of Information Technology
📫 Academic Services
Journal Reviewer
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- International Journal of Computer Vision (IJCV)
- IEEE Transactions on Image Processing (TIP)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Conference Reviewer
- International Conference on Intelligent Robots and Systems (IROS) 2022
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
- Advances in Neural Information Processing Systems (NeurIPS) 2024
- International Conference on Learning Representations (ICLR) 2024
💻 Experience
- 2022.09 - present, PhD student, at Uppsala university, Sweden.
- 2021.07 - 2022.07, Research Assistant, at Megvii Technology, China.