BriefGPT.xyz
Jul, 2023
学习压缩图像时去噪的重要性
On the Importance of Denoising when Learning to Compress Images
HTML
PDF
Benoit Brummer, Christophe De Vleeschouwer
TL;DR
本文提出在训练编解码器时明确地学习图像去噪任务，通过监督编解码器的噪声-干净图像对，得出训练多种噪声水平图像组成的混合模型效果最佳，能在压缩、去噪任务中优于一组去噪-压缩模型。
Abstract
image noise
is ubiquitous in photography. However,
image noise
is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par results in both rate and distort
→