Transformer-based Learned Image Compression for Joint Decoding and Denoising
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916131996958720 |
|---|---|
| author | Chen, Yi-Hsin Ho, Kuan-Wei Tsai, Shiau-Rung Lin, Guan-Hsun Gnutti, Alessandro Peng, Wen-Hsiao Leonardi, Riccardo |
| author_facet | Chen, Yi-Hsin Ho, Kuan-Wei Tsai, Shiau-Rung Lin, Guan-Hsun Gnutti, Alessandro Peng, Wen-Hsiao Leonardi, Riccardo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12888 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transformer-based Learned Image Compression for Joint Decoding and Denoising Chen, Yi-Hsin Ho, Kuan-Wei Tsai, Shiau-Rung Lin, Guan-Hsun Gnutti, Alessandro Peng, Wen-Hsiao Leonardi, Riccardo Image and Video Processing 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. |
| title | Transformer-based Learned Image Compression for Joint Decoding and Denoising |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2402.12888 |