TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Convolutional Neural Network with Median Layers for Denois...

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

Luming Liang, Sen Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin

2019-08-18DenoisingSalt-And-Pepper Noise Removal
PaperPDFCode(official)

Abstract

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes the extremely high-level s&p noise without performing any non-trivial preprocessing tasks, which is different from all the existing literature in s&p noise removal. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts the signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data. The source code has been released for public evaluation and use (https://github.com/llmpass/medianDenoise).

Results

TaskDatasetMetricValueModel
DenoisingBSD300 Noise Level 30%PSNR40.9CNN (Median Layers)
DenoisingBSD300 Noise Level 50%PSNR37.28CNN (Median Layers)
DenoisingKodak24 Noise Level 50%PSNR34.35CNN (Median Layers)
DenoisingKodak24 Noise Level 70%PSNR31.56CNN (Median Layers)
DenoisingBSD300 Noise Level 70%PSNR32.4CNN (Median Layers)
DenoisingKodak24 Noise Level 30%PSNR36.39CNN (Median Layers)
3D ArchitectureBSD300 Noise Level 30%PSNR40.9CNN (Median Layers)
3D ArchitectureBSD300 Noise Level 50%PSNR37.28CNN (Median Layers)
3D ArchitectureKodak24 Noise Level 50%PSNR34.35CNN (Median Layers)
3D ArchitectureKodak24 Noise Level 70%PSNR31.56CNN (Median Layers)
3D ArchitectureBSD300 Noise Level 70%PSNR32.4CNN (Median Layers)
3D ArchitectureKodak24 Noise Level 30%PSNR36.39CNN (Median Layers)

Related Papers

fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting2025-07-17Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models2025-07-17Similarity-Guided Diffusion for Contrastive Sequential Recommendation2025-07-16HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing2025-07-15AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air2025-07-15A statistical physics framework for optimal learning2025-07-10LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models2025-07-08Unconditional Diffusion for Generative Sequential Recommendation2025-07-08