Work

JPEG Information Regularized Deep Image Prior for Denoising

Year: 2023

Type: conference-paper

Abstract: 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.

Source: Proceedings - International Conference on Image Processing

DOI: 10.1109/icip49359.2023.10223088

Authors: Tsukasa Takagi, Shinya Ishizaki, Shin-ichi Maeda

Institutions: Preferred Networks (Japan), Kyoto University

Language: English

Topic: Image and Signal Denoising Methods

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Ministry of Internal Affairs and Communications

Award: G7222400979