πŸ‘‹ Bio

I am currently a second-year Ph.D. student at the School of Engineering in the Westlake University, in collaboration with Zhejiang University. My PhD advisor is Prof. Peidong Liu. Before that, I received my Bachelor and Master Degree from Huazhong University of Science and Technology respectively in 2019 and 2022.

My research interest lies in 3D vision (e.g. Neural Rendering, Dynamic Scene Understanding), HumanAvatar and Generative Models.

🌟 News

07/2024: Our papers BAD-Gaussians and BeNeRF are accepted to ECCV 2024! Thanks to all collaborators!
01/2024: Our paper USB-NeRF is accepted to ICLR 2024! Thanks to all collaborators!
02/2023: Our paper BAD-NeRF is accepted to CVPR 2023! Thanks to all collaborators!

πŸ“– Publications

* denotes equal contribution or advising; † denotes corresponding author.

MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation
arXiv 2024

MBA-SLAM can accurately estimate the local camera motion trajectories within the exposure time and recovers the high quality 3D scene from blurry sequences.

BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream
ECCV 2024

We explore the possibility of recovering the neural radiance fields and camera motion trajectory from a single blurry image with its events.

BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
ECCV 2024

BAD-Gaussians successfully deblurs severe motion-blurred images, synthesizes higher-quality novel views, and achieves real-time rendering, surpassing previous SOTA implicit deblurring rendering methods.

SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects
arXiv 2023
Peng Wang, Haiming Yao, Wenyong Yu†

We address the challenge of detecting object defects through the self-supervised learning approach of solving the jigsaw puzzle problem.

USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
ICLR 2024

USB-NeRF can remove rolling shutter effect and recover high-fidelity high frame-rate global shutter video from a sequence of rolling shutter images.

BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
CVPR 2023
Peng Wang, Lingzhe Zhao, Ruijie Ma, Peidong Liu†

BAD-NeRF jointly learns the 3D representation and optimizes the camera motion trajectories within exposure time from blurry images and inaccurate initial poses.
Nov. 2023 update: we have released the NeRFstudio version Bad-RFs.

πŸš€ Projects

Bad-RFs: Bundle-adjusted Radiance Fields from Degraded Images with Continuous-time Motion Models
Research Project, 2023

BAD-NeRFstudio can shorten the training of BAD-NeRF to minutes.

πŸ… Awards

  • Muyuan Fellowship (20000 CNY), Westlake University-Muyuan joint Research Institute, 2022
  • National Academic First Class Scholarship for Postgraduates, HUST, 2021, 2022
  • 7th in HUAWEI Software Elite Challenge (Huazhong Division), 2020
  • 3rd Prize in China Youth Cup National College Students Mathematical Modeling Competition, 2020
  • 1st Prize of the Robot Innovation Design Competition of HUST, 2019