Lune

CVPR2023Top-tier venue

Structured Kernel Estimation for Photon-Limited Deconvolution

Yash Sanghvi, Zhiyuan Mao, Stanley H. Chan

Abstract

Images taken in a low light condition with the presence of camera shake suffer from motion blur and photon shot noise. While state-of-the-art image restoration networks show promising results, they are largely limited to well-illuminated scenes and their performance drops significantly when photon shot noise is strong. In this paper, we propose a new blur estimation technique customized for photon-limited conditions. The proposed method employs a gradient-based backpropagation method to estimate the blur kernel. By modeling the blur kernel using a low-dimensional representation with the key points on the motion trajectory, we significantly reduce the search space and improve the regularity of the kernel estimation problem. When plugged into an iterative framework, our novel low-dimensional representation provides improved kernel estimates and hence significantly better deconvolution performance when compared to end-to-end trained neural networks. The source code and pretrained mdoels are available at https://github. com / sanghviyashiitb / structured -kernel -cvpr23 Vectorize

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Uformer: A General U-Shaped Transformer for Image Restoration cites Deblurring by Realistic Blurring
  • Uformer: A General U-Shaped Transformer for Image Restoration cites DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
  • Rethinking Coarse-to-Fine Approach in Single Image Deblurring cites DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
  • Restormer: Efficient Transformer for High-Resolution Image Restoration cites Uformer: A General U-Shaped Transformer for Image Restoration
  • Restormer: Efficient Transformer for High-Resolution Image Restoration cites Rethinking Coarse-to-Fine Approach in Single Image Deblurring
  • Restormer: Efficient Transformer for High-Resolution Image Restoration cites Deblurring by Realistic Blurring
  • Restormer: Efficient Transformer for High-Resolution Image Restoration cites DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
  • Deblurring by Realistic Blurring cites DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. I2EBench: A Comprehensive Benchmark for Instruction-based Image EditingYiwei Ma, Jiayi Ji, Ke Ye, Weihuang Lin et al.NeurIPS 2024 · 67 citations

Builds on7

  1. Restormer: Efficient Transformer for High-Resolution Image RestorationSyed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat et al.CVPR 2022 · 3,348 citations
  2. Uformer: A General U-Shaped Transformer for Image RestorationZhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou et al.CVPR 2022 · 1,970 citations
  3. DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and BetterOrest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang WangICCV 2019 · 1,100 citations
  4. Rethinking Coarse-to-Fine Approach in Single Image DeblurringSung-Jin Cho, Seo-Won Ji, Jun-Pyo Hong, Seung-Won Jung et al.ICCV 2021 · 799 citations
  5. Deblurring by Realistic BlurringKaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma et al.CVPR 2020

Related papers

  1. Spectrum-to-Kernel Translation for Accurate Blind Image Super-ResolutionGuangpin Tao, Xiaozhong Ji, Wenzhuo Wang, Shuo Chen et al.NeurIPS 2021 · 27 citations
  2. Deep Learning for Handling Kernel/model Uncertainty in Image DeconvolutionYuesong Nan, Hui JiCVPR 2020
  3. Self-Diffusion Driven Blind ImagingYanlong Yang, Guanxiong LuoCVPR 2026
  4. Deblurring Using Analysis-Synthesis Networks PairAdam Kaufman, Raanan FattalCVPR 2020
  5. A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-ResolutionZhixiong Yang, Jingyuan Xia, Shengxi Li, Xinghua Huang et al.CVPR 2024 · 26 citations
Dusk over the sea between two cliffs drawn in fine vertical lines