๐ Hi there!
I am currently a joint PhD student at the Computer Graphics Lab of ETH Zรผrich and DisneyResearch|Studios, supervised by Prof. Markus Gross and Dr. Christopher Schroers. I also spent 4 months working on low-level vision at the Computer Vision Lab, ETH Zรผrich. Before that, I received my M.E. and B.E. degrees respectively in 2023 and 2020 from the Electronic Information School of Wuhan University, where I work closely with Prof. Lei Yu on event-based vision. I am a lifelong learner with broad interests, including computer vision, signal processing, and neuromorphic computing. I am particularly interested in achieving robust perception in complex environments for real-world applications.
๐ฅ News
๐ Publications
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Xiang Zhang, Bingxin Ke, Hayko Riemenschneider, Nando Metzger, Anton Obukhov, Markus Grossโ , Konrad Schindler, Christopher Schroersโ
[arXiv]
- We propose BetterDepth to boost zero-shot MDE methods with plug-and-play diffusion refiners, achieving robust affine-invariant MDE performance with fine-grained details.
- We design global pre-alignment and local patch masking strategies to enable learning detail refinement from small-scale synthetic datasets while preserving rich prior knowledge from pre-trained MDE models for zero-shot transfer.
HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
Xiang Zhang, Yulun Zhang, Fisher Yu
- We propose a simple yet effective strategy (HiT-SR) to convert popular transformer-based SR methods to our hierarchical transformers, boosting SR performance by exploiting multi-scale features and long-range dependencies.
- We design a spatial-channel correlation method to efficiently leverage spatial and channel features with linear computational complexity to window sizes, enabling utilization of large hierarchical windows, e.g., $64\times64$ windows.
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Xiang Zhang, Lei Yuโ , Wen Yang, Jianzhuang Liu, Gui-Song Xia
- A scale-aware network is designed to allow flexible setups of input spatial resolutions and enable learning from different temporal scales of motion blur.
- A self-supervised learning framework is proposed for model training with real-world data and performance generalization in spatial and temporal domains.
- A multi-scale real-world blurry dataset (MS-RBD) is constructed to facilitate the evaluation of deblurring performance in real-world scenarios.
Learning to See Through with Events
Lei Yuโ , Xiang Zhang, Wei Liao, Wen Yang, Gui-Song Xia
- An event-based synthetic aperture imaging (E-SAI) algorithm is proposed to see through dense occlusions even under extreme lighting conditions.
- A hybrid network composed of an spiking encoder and a convolutional decoder is designed to mitigate the disturbances from occlusions and guarantee the overall reconstruction performance.
Unifying Motion Deblurring and Frame Interpolation with Events
Xiang Zhang, Lei Yuโ
- We present a unified framework for event-based video deblurring and interpolation (EVDI).
- By utilizing the constraints between cross-modal frames and events, a fully self-supervised learning method is proposed to enable network training with real-world data without requiring ground-truth images.
-
TPAMI 2024
CrossZoom: Simultaneous Motion Deblurring and Event Super-Resolving, Chi Zhang, Xiang Zhang, Mingyuan Lin, Cheng Li, Chu He, Wen Yang, Gui-Song Xia, Lei Yu. | [Website] -
TIP 2024
Neuromorphic Synergy for Video Binarization, Shijie Lin, Xiang Zhang, Lei Yang, Lei Yu, Bin Zhou, Xiaowei Luo, Wenping Wang, Jia Pan. | [Code&Dataset] [Youtube] [Bilibili] -
TPAMI 2023
Learning to Super-Resolve Blurry Images with Events, Lei Yuโ , Bishan Wang, Xiang Zhang, Haijian Zhang, Wen Yang, Jianzhuang Liu, Gui-Song Xia. | [Code] -
TSP 2022
Spiking Sparse Recovery with Non-convex Penalties, Xiang Zhang, Lei Yuโ , Gang Zheng, Yonina C. Eldar. -
CVPR 2022
Synthetic Aperture Imaging with Events and Frames, Wei Liao*, Xiang Zhang*, Lei Yuโ , Shijie Lin, Wen Yang, Ning Qiao. | [Code] [Dataset] -
CVPR 2021
Event-based Synthetic Aperture Imaging with a Hybrid Network, Xiang Zhang*, Wei Liao*, Lei Yuโ , Wen Yang, Gui-Song Xia. (Oral, Best Paper Candidate) | [Code] [Dataset] [Youtube]
* means equal contribution and โ indicates my supervisor.
๐ฌ Invited Talks
- 2021 & 2022, Introduction to Spiking Neural Networks, Wuhan University
- 2021, Event-based Synthetic Aperture Imaging with a Hybrid Network, VALSE Webinar | [Bilibili]
- 2021, Event-based Synthetic Aperture Imaging with a Hybrid Network, CSIG-3DV Student Forum
๐ป Services
- Conference Review: CVPR, ICCV, ECCV, NeurIPS, ICLR
- Journal Review: Springer IJCV, Springer MIR
๐น Misc
- ๐ธ I love rock and hip-hop music. Mayday, Jay Chou, and Pharaoh are my favoriate.
- ๐ I enjoy reading all kinds of books. Echoโs story inspired me about love and traveling. My recent favoriate is the sci-fi novel The Three Body Problem written by Cixin Liu.
- ๐ฎ I often relax by playing games, including roguelike games like Slay the Spire and card games like Hearthstone. I recently played It Takes Two with my girlfriend, and it was super fun!
- ๐ซ It always excites me when experiencing new cultures in new places. Here are some photos I took during my trips.