JPEG Information Regularized Deep Image Prior for Denoising

DOI DOI オープンアクセス

説明

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.

IEEE International Conference on Image Processing (ICIP 2023)

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ