PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors

By Zeyuan Chen, Yangchao Wang, Yang Yang, Dong Liu. Computer Vision and Pattern Recognition, 2021

354 citations recorded by the source corpus.

Deep learning-based methods have achieved remarkable performance for image dehazing. However, previous studies are mostly focused on training models with synthetic hazy images, which incurs performance drop when the models are used for real-world hazy images. We propose a Principled Synthetic-to-real Dehazing (PSD) framework to improve the generalization performance of dehazing. Starting from a dehazing model backbone that is pre-trained on synthetic data, PSD exploits real hazy images to fine-tune the model in an unsupervised fashion. For the fine-tuning, we leverage several well-grounded physical priors and combine them into a prior loss committee. PSD allows for most of the existing dehazing models as its backbone, and the combination of multiple physical priors boosts dehazing significantly. Through extensive experiments, we demonstrate that our PSD framework establishes the new state-of-the-art performance for real-world dehazing, in terms of visual quality assessed by no-reference quality metrics as well as subjective evaluation and downstream task performance indicator.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8d908939833f8bef1ee0c2820f546aca6bc947b5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Chongyi Li
  2. Chunle Guo
  3. Runmin Cong
  4. Wenqi Ren
  5. Saeed Anwar
  6. Qixin Yan
  7. Chunli Zhu
  8. Liheng Bian

Citations in the corpus