SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.10291 · 2020

Spatial-Adaptive Network for Single Image Denoising

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network structure could alleviate these problems, but more computational overhead is needed. In this paper, we propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal. To adapt to changes in spatial textures and edges, we design a residual spatial-adaptive block. Deformable convolution is introduced to sample the spatially correlated features for weighting. An encoder-decoder structure with a context block is introduced to capture multiscale information. With noise removal from the coarse to fine, a high-quality noisefree image can be obtained. We apply our method to both synthetic and real noisy image datasets. The experimental results demonstrate that our method can surpass the state-of-the-art denoising methods both quantitatively and visually.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2001.10291")
get_code_for_paper("2001.10291")
have("2001.10291")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2001.10291.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2001.10291.svg)](https://syntology.ai/paper/2001.10291)

Connect an agent — have() is free.