SLIC: A Learned Image Codec Using Structure and Color
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911767898095616 |
|---|---|
| author | Prativadibhayankaram, Srivatsa Panda, Mahadev Prasad Richter, Thomas Sparenberg, Heiko Fößel, Siegfried Kaup, André |
| author_facet | Prativadibhayankaram, Srivatsa Panda, Mahadev Prasad Richter, Thomas Sparenberg, Heiko Fößel, Siegfried Kaup, André |
| contents | We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV channels in the encoder, where the features from various stages are combined to obtain the latent representation. An autoregressive context model is employed for backward adaptation and a hyperprior block for forward adaptation. Various experiments are carried out to study and analyze the performance of the proposed model, and to compare it with other image codecs. We also illustrate the advantages of our method through the visualization of channel impulse responses, latent channels and various ablation studies. The model achieves Bjøntegaard delta bitrate gains of 7.5% and 4.66% in terms of MS-SSIM and CIEDE2000 metrics with respect to other state-of-the-art reference codecs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17246 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SLIC: A Learned Image Codec Using Structure and Color Prativadibhayankaram, Srivatsa Panda, Mahadev Prasad Richter, Thomas Sparenberg, Heiko Fößel, Siegfried Kaup, André Image and Video Processing Computer Vision and Pattern Recognition We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV channels in the encoder, where the features from various stages are combined to obtain the latent representation. An autoregressive context model is employed for backward adaptation and a hyperprior block for forward adaptation. Various experiments are carried out to study and analyze the performance of the proposed model, and to compare it with other image codecs. We also illustrate the advantages of our method through the visualization of channel impulse responses, latent channels and various ablation studies. The model achieves Bjøntegaard delta bitrate gains of 7.5% and 4.66% in terms of MS-SSIM and CIEDE2000 metrics with respect to other state-of-the-art reference codecs. |
| title | SLIC: A Learned Image Codec Using Structure and Color |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.17246 |