Papers › NBNet: Noise Basis Learning for Image Denoising with Subspace Projection

NBNet: Noise Basis Learning for Image Denoising with Subspace Projection

30 Dec 2020CVPR 2021 1arXiv:2012.15028archive 2025-07-28

Shen Cheng, Yuzhi Wang, Haibin Huang, Donghao Liu, Haoqiang Fan, Shuaicheng Liu

In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous works, we propose to tackle this challenging problem from a new perspective: noise reduction by image-adaptive projection. Specifically, we propose to train a network that can separate signal and noise by learning a set of reconstruction basis in the feature space. Subsequently, image denosing can be achieved by selecting corresponding basis of the signal subspace and projecting the input into such space. Our key insight is that projection can naturally maintain the local structure of input signal, especially for areas with low light or weak textures. Towards this end, we propose SSA, a non-local subspace attention module designed explicitly to learn the basis generation as well as the subspace projection. We further incorporate SSA with NBNet, a UNet structured network designed for end-to-end image denosing. We conduct evaluations on benchmarks, including SIDD and DND, and NBNet achieves state-of-the-art performance on PSNR and SSIM with significantly less computational cost.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

megvii-research/NBNet officialmentioned in papermentioned on GitHub report
leonmakise/NBNet_Pytorch mentioned on GitHubpytorch report
megengine/nbnet mentioned on GitHub report
pminhtam/NBNet mentioned 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

DenoisingImage DenoisingSSIM

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Denoising DND NBNet PSNR (sRGB) 39.89 #6 of 16 Archive leaderboard report
Image Denoising DND NBNet SSIM (sRGB) 0.955 #6 of 16 Archive leaderboard report
Image Denoising SIDD NBNet SSIM (sRGB) 0.973 #21 of 22 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.

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