Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Progressive Feature Fusion Network for Realistic Image Dehazing

About

Single image dehazing is a challenging ill-posed restoration problem. Various prior-based and learning-based methods have been proposed. Most of them follow a classic atmospheric scattering model which is an elegant simplified physical model based on the assumption of single-scattering and homogeneous atmospheric medium. The formulation of haze in realistic environment is more complicated. In this paper, we propose to take its essential mechanism as "black box", and focus on learning an input-adaptive trainable end-to-end dehazing model. An U-Net like encoder-decoder deep network via progressive feature fusions has been proposed to directly learn highly nonlinear transformation function from observed hazy image to haze-free ground-truth. The proposed network is evaluated on two public image dehazing benchmarks. The experiments demonstrate that it can achieve superior performance when compared with popular state-of-the-art methods. With efficient GPU memory usage, it can satisfactorily recover ultra high definition hazed image up to 4K resolution, which is unaffordable by many deep learning based dehazing algorithms.

Kangfu Mei, Aiwen Jiang, Juncheng Li, Mingwen Wang• 2018

Related benchmarks

TaskDatasetResultRank
Image DehazingHazeRD
SSIM0.808
29
Image DehazingSOTS indoor and outdoor
PSNR29.22
12
Image DehazingI-HAZE
PSNR16.01
12
Image DehazingO-HAZE
PSNR18.76
12
Object DetectionReal-world adverse weather captures
mAP (Easy)91.37
10
Image DescatteringSynthetic dataset
LPIPS0.827
10
Image DescatteringFog Chamber Measurements
LPIPS0.841
10
Showing 7 of 7 rows

Other info

Follow for update