Joint Image Compression and Denoising via Latent-Space Scalability

TL;DR

This paper introduces a learning-based image compression framework that jointly performs denoising and compression, enabling scalable decoding of noisy and clean images with significant bitrate savings over traditional methods.

Contribution

It proposes a novel latent-space scalable codec that allows joint denoising and compression, improving efficiency and flexibility compared to separate processing.

Findings

Significant bitrate savings over cascade methods

Scalable decoding of noisy and clean images

Effective joint denoising and compression

Abstract

When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court evidence and image forensics. This means that noise itself needs to be coded, in addition to the clean image itself. In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly. The latent space of the image codec is organized in a scalable manner such that the clean image can be decoded from a subset of the latent space (the base layer), while the noisy image is decoded from the full latent space at a higher rate. Using a subset of the latent space for the denoised image allows denoising to be carried out at a lower rate. Besides providing a scalable representation of the noisy input image, performing denoising jointly with compression makes intuitive sense because noise is hard to compress; hence, compressibility is one of the criteria that may help distinguish noise from the signal. The proposed codec is compared against established compression and denoising benchmarks, and the experiments reveal considerable bitrate savings compared to a cascade combination of a state-of-the-art codec and a state-of-the-art denoiser.