WeChat Mini Program
Old Version Features

Transformer-based Learned Image Compression for Joint Decoding and Denoising

Yi-Hsin Chen, Kuan-Wei Ho, Shiau-Rung Tsai, Guan-Hsun Lin,Alessandro Gnutti,Wen-Hsiao Peng,Riccardo Leonardi

2024 PICTURE CODING SYMPOSIUM, PCS 2024(2024)

Natl Yang Ming Chiao Tung Univ

Cited 0|Views11
Abstract
This work introduces a Transformer-based image compression system. It has theflexibility to switch between the standard image reconstruction and thedenoising reconstruction from a single compressed bitstream. Instead oftraining separate decoders for these tasks, we incorporate two add-on modulesto adapt a pre-trained image decoder from performing the standard imagereconstruction to joint decoding and denoising. Our scheme adopts a two-prongedapproach. It features a latent refinement module to refine the latentrepresentation of a noisy input image for reconstructing a noise-free image.Additionally, it incorporates an instance-specific prompt generator that adaptsthe decoding process to improve on the latent refinement. Experimental resultsshow that our method achieves a similar level of denoising quality to traininga separate decoder for joint decoding and denoising at the expense of only amodest increase in the decoder's model size and computational complexity.
More
Translated text
Key words
Learned image compression,compressed-domain image denoising,Transformer
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined