This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate decoders for these tasks, we incorporate two add-on modules to adapt a pre-trained image decoder from performing the standard image reconstruction to joint decoding and denoising. Our scheme adopts a two-pronged approach. It features a latent refinement module to refine the latent representation of a noisy input image for reconstructing a noise-free image. Additionally, it incorporates an instance-specific prompt generator that adapts the decoding process to improve on the latent refinement. Experimental results show that our method achieves a similar level of denoising quality to training a separate decoder for joint decoding and denoising at the expense of only a modest increase in the decoder's model size and computational complexity.
@article{arxiv.2402.12888,
title = {Transformer-based Learned Image Compression for Joint Decoding and Denoising},
author = {Yi-Hsin Chen and Kuan-Wei Ho and Shiau-Rung Tsai and Guan-Hsun Lin and Alessandro Gnutti and Wen-Hsiao Peng and Riccardo Leonardi},
journal= {arXiv preprint arXiv:2402.12888},
year = {2024}
}