DND

Darmstadt Noise Dataset

Dataset Information
Modalities
Images
License
Unknown
Homepage
Official Website
Contents

Overview

Benchmarking Denoising Algorithms with Real Photographs

This dataset consists of 50 pairs of noisy and (nearly) noise-free images captured with four consumer cameras. Since the images are of very high-resolution, the providers extract 20 crops of size 512 × 512 from each image, thus yielding a total of 1000 patches.

Variants: DND

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Image Denoising DualDn DualDn: Dual-domain Denoising via Differentiable … 2024-09-27
Denoising DRANet Dual Residual Attention Network for … 2023-05-07
Image Denoising PNGAN Learning to Generate Realistic Noisy … 2022-04-06
Image Denoising MAXIM-3S MAXIM: Multi-Axis MLP for Image … 2022-01-09
Image Denoising Restormer Restormer: Efficient Transformer for High-Resolution … 2021-11-18
Image Denoising Uformer-B Uformer: A General U-Shaped Transformer … 2021-06-06
Image Denoising MPRNet Multi-Stage Progressive Image Restoration 2021-02-04
Image Denoising NBNet NBNet: Noise Basis Learning for … 2020-12-30
Image Denoising DANet+ Dual Adversarial Network: Toward Real-world … 2020-07-12
Image Denoising CycleISP CycleISP: Real Image Restoration via … 2020-03-17
Image Denoising MIRNet Learning Enriched Features for Real … 2020-03-15
Image Denoising AINDNet Transfer Learning from Synthetic to … 2020-02-26
Image Denoising SADNet Spatial-Adaptive Network for Single Image … 2020-01-28
Image Denoising VDN Variational Denoising Network: Toward Blind … 2019-08-29
Image Denoising RIDNet Real Image Denoising with Feature … 2019-04-16
Image Denoising CBDNet Toward Convolutional Blind Denoising of … 2018-07-12

Research Papers

Recent papers with results on this dataset:

External Links: