Joint Image Compression and Denoising via Latent-Space Scalability

Alvar, Saeed Ranjbar; Ulhaq, Mateen; Choi, Hyomin; Bajić, Ivan V.

doi:10.48550/arxiv.2205.01874

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preliminary work in the compressed domain image denoising field proposed a non-normative decoder solution able to combine decoding and denoising operations, while reducing the computational complexity of the pipeline. 22 A different approach for latent-space denoising was proposed by Alvar et al, 23 where a joint compression and denoising network based on a scalable latent space allowed to achieve BD-rate savings and improve the quality of images simultaneously. A joint compression and denoising method designed for satellite images was proposed, by training both the encoder and the decoder of a learning-based compression algorithm with an alternative loss function.…”

Section: Related Workmentioning

confidence: 99%

On combining denoising with learning-based image decoding

Larigauderie¹,

Testolina²,

Ebrahimi³

2022

Applications of Digital Image Processing XLV

View full text Add to dashboard Cite

Noise is an intrinsic part of any sensor and is present, in various degrees, in any content that has been captured in real life environments. In imaging applications, several pre-and post-processing solutions have been proposed to cope with noise in captured images. More recently, learning-based solutions have shown impressive results in image enhancement in general, and in image denoising in particular. In this paper, we review multiple novel solutions for image denoising in the compressed domain, by integrating denoising operations into the decoder of a learning-based compression method. The paper starts by explaining the advantages of such an approach from different points of view. We then describe the proposed solutions, including both blind and non-blind methods, comparing them to state of the art methods. Finally, conclusions are drawn from the obtained results, summarizing the advantages and drawbacks of each method.

show abstract

Section: Related Workmentioning

confidence: 99%