Papers › Single image dehazing for a variety of haze scenarios using back projected pyramid network

Single image dehazing for a variety of haze scenarios using back projected pyramid network

15 Aug 2020arXiv:2008.06713archive 2025-07-28

Ayush Singh, Ajay Bhave, Dilip K. Prasad

Learning to dehaze single hazy images, especially using a small training dataset is quite challenging. We propose a novel generative adversarial network architecture for this problem, namely back projected pyramid network (BPPNet), that gives good performance for a variety of challenging haze conditions, including dense haze and inhomogeneous haze. Our architecture incorporates learning of multiple levels of complexities while retaining spatial context through iterative blocks of UNets and structural information of multiple scales through a novel pyramidal convolution block. These blocks together for the generator and are amenable to learning through back projection. We have shown that our network can be trained without over-fitting using as few as 20 image pairs of hazy and non-hazy images. We report the state of the art performances on NTIRE 2018 homogeneous haze datasets for indoor and outdoor images, NTIRE 2019 denseHaze dataset, and NTIRE 2020 non-homogeneous haze dataset.

PaperPDFCode

Code

ayu-22/BPPNet-Back-Projected-Pyramid-Network officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image DehazingNonhomogeneous Image DehazingSingle Image Dehazing

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Dehazing Dense-Haze BPPNet PSNR 17.01 #3 of 5 Archive leaderboard report
Image Dehazing Dense-Haze BPPNet SSIM 0.613 #3 of 5 Archive leaderboard report
Image Dehazing I-Haze BPPNet PSNR 22.56 #2 of 4 Archive leaderboard report
Image Dehazing I-Haze BPPNet SSIM 0.8994 #2 of 4 Archive leaderboard report
Image Dehazing O-Haze BPPNet PSNR 24.27 #5 of 7 Archive leaderboard report
Image Dehazing O-Haze BPPNet SSIM 0.8919 #5 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections