# Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision

arXiv: https://arxiv.org/abs/2007.05220 · HTML: https://mlsanity.com/paper/2007.05220/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

## Built on by (most cited first, 1 of 1)

- [Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning](https://mlsanity.com/paper/2203.07677/) (2022)

## Abstract (arXiv)

Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from performance degradation near depth borders, where depth tends to vary abruptly. Hence, we propose to anneal the depth border degradation in unpaired image dehazing with cyclic perceptual-depth supervision. Coupled with the dual-path feature re-using backbones of the generators and discriminators, our model achieves 20.36 Peak Signal-to-Noise Ratio (PSNR) on NYU Depth V2 dataset, significantly outperforming its predecessors with reduced Floating Point Operations (FLOPs).