Image denoising is a representative image restoration task in computer vision. Recent progress of image denoising from only noisy images has attracted much attention. Deep image prior (DIP) demonstrated successful image denoising from only a noisy image by inductive bias of convolutional neural network architectures without any pre-training. The major challenge of DIP based image denoising is that DIP would completely recover the original noisy image unless applying early stopping. For early stopping without a ground-truth clean image, we propose to monitor JPEG file size of the recovered image during optimization as a proxy metric of noise levels in the recovered image. Our experiments show that the compressed image file size works as an effective metric for early stopping.
@article{arxiv.2310.00894,
title = {JPEG Information Regularized Deep Image Prior for Denoising},
author = {Tsukasa Takagi and Shinya Ishizaki and Shin-ichi Maeda},
journal= {arXiv preprint arXiv:2310.00894},
year = {2023}
}
Comments
IEEE International Conference on Image Processing (ICIP 2023)