Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models

Research output: Contribution to journalArticlepeer-review


Image restoration under adverse weather conditions has been of significant interest for various computer vision applications. Recent successful methods rely on the current progress in deep neural network architectural designs (e.g., with vision transformers). Motivated by the recent progress achieved with state-of-the-art conditional generative models, we present a novel patch-based image restoration algorithm based on denoising diffusion probabilistic models. Our patch-based diffusion modeling approach enables size-agnostic image restoration by using a guided denoising process with smoothed noise estimates across overlapping patches during inference. We empirically evaluate our model on benchmark datasets for image desnowing, combined deraining and dehazing, and raindrop removal. We demonstrate our approach to achieve state-of-the-art performances on both weather-specific and multi-weather image restoration, and experimentally show strong generalization to real-world test images.
Original languageEnglish
Pages (from-to)10346-10357
Number of pages12
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number8
Early online date2023
Publication statusPublished - 1 Aug 2023


  • Computational modeling
  • Data models
  • Dehazing
  • denoising diffusion models
  • deraining
  • desnowing
  • Image restoration
  • Meteorology
  • Noise reduction
  • patch-based image restoration
  • Rain
  • raindrop removal
  • Task analysis
  • Denoising diffusion models
  • dehazing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics

Fields of Expertise

  • Information, Communication & Computing


Dive into the research topics of 'Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models'. Together they form a unique fingerprint.

Cite this