Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910287176663040 |
|---|---|
| author | Ladune, Théo Philippe, Pierrick Clare, Gordon Henry, Félix Leguay, Thomas |
| author_facet | Ladune, Théo Philippe, Pierrick Clare, Gordon Henry, Félix Leguay, Thomas |
| contents | This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02156 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder Ladune, Théo Philippe, Pierrick Clare, Gordon Henry, Félix Leguay, Thomas Image and Video Processing This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge. |
| title | Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2401.02156 |