Lei Sun (孙磊)
I am a doctoral student at Zhejiang University under the supervision of Prof. Kaiwei Wang .
I am also a visiting doctoral student at Computer Vision Lab,
ETH Zurich under the supervision of Prof. Luc Van Gool.
Before that, I received my bachelor's degree from Beijing Institute of Technology.
I am looking for post-doc positions or job opportunities related to event camera, low-level image process, and environment perception algorithms.
Email  / 
CV  / 
Google Scholar  / 
Linkedin  / 
Github
|
|
Research
I'm interested in computer vision, machine learning, image processing and event cameras. First-author papers are highlighted.
|
|
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
Lei Sun,
Christos Sakaridis,
Jingyun Liang,
Qi Jiang,
Kailun Yang,
Peng Sun,
Yaozu Ye,
Kaiwei Wang,
Luc Van Gool
ECCV, 2022   (Oral Presentation, rate:2.7%)
project page
/
codes
/
arXiv
We present a novel event-based deblurring method that improves the previous state-of-the-art by 2.47 dB.
|
|
Compact and lightweight panoramic annular lens for computer vision tasks
Shaohua Gao, Lei Sun, Qi Jiang, Hao Shi, Jia Wang, Kaiwei Wang, Jian Bai
Optical Express, 2022
Designing a lightweight panoramic annular lens with physical-based image enhancement model.
|
|
High-performance panoramic annular lens design for real-time semantic segmentation on aerial imagery
Jia Wang, Kailun Yang, Shaohua Gao, Lei Sun, Chenxi Zhu, Kaiwei Wang, Jian Bai
Optical Engineering 61 (3), 035101, 2022
Designing a panoramic annular lens (PAL) system with 4K high resolution for aerial image segmentation.
|
|
Aerial-PASS: panoramic annular scene segmentation in drone videos
Lei Sun, Jia Wang, Kailun Yang, Kaikai Wu, Xiangdong Zhou, Kaiwei Wang, Jian Bai
European Conference on Mobile Robots (ECMR) 2021
Designing a specific semantic segmentation for aerial panoramic images.
|
|
Real-time fusion network for RGB-D semantic segmentation incorporating unexpected obstacle detection for road-driving images
Lei Sun, Kailun Yang, Xinxin Hu, Weijian Hu, Kaiwei Wang
IEEE Robotics and Automation Letters and IROS, 2020
codes
A real-time RGB-D fusion semantic segmentation framework with small obstacle detection.
|
|
A comparative study in real-time scene sonification for visually impaired people
Weijian Hu, Kaiwei Wang, Kailun Yang, Ruiqi Cheng, Yaozu Ye, Lei Sun, Zhijie Xu
Sensors 20 (11), 3222, 2020
Propose three different auditory-based interaction methods which convey raw depth images,
obstacle information and path information respectively to visually impaired people.
|
|
A panoramic localizer based on coarse-to-fine descriptors for navigation assistance
Yicheng Fang, Kailun Yang, Ruiqi Cheng, Lei Sun, Kaiwei Wang
Sensors 20 (15), 4177, 2020
Propose a panoramic
localizer, which is based on coarse-to-fine descriptors, leveraging panoramas for omnidirectional
perception and sufficient FoV up to 360◦.
|
|
A wearable vision-to-audio sensory substitution device for blind assistance and the correlated neural substrates
Yaozu Ye, Kaiwei Wang, Weijian Hu, Huabing Li, Kailun Yang, Lei Sun, Zuobing Chen
Journal of Physics: Conference Series 1229 (1), 012026, 2019
Develop a wearable system to transform the
spatial information captured by camera into a voice description and fed it back to blind users.
|
|
See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
Lei Sun, Kailun Yang, Kaiwei Wang, Kaite Xiang
Artificial Intelligence and Machine Learning in Defense Applications, SPIE 1229 (1), 012026, 2019
Propose a
framework to alleviate the accuracy decline when semantic segmentation is taken to adverse conditions by using
Generative Adversarial Networks (GANs).
|
|