Learning-Based Conditional Image Coder Using Color Separation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917598445174784 |
|---|---|
| author | Jia, Panqi Koyuncu, Ahmet Burakhan Gaikov, Georgii Karabutov, Alexander Alshina, Elena Kaup, Andre |
| author_facet | Jia, Panqi Koyuncu, Ahmet Burakhan Gaikov, Georgii Karabutov, Alexander Alshina, Elena Kaup, Andre |
| contents | Recently, image compression codecs based on Neural Networks(NN) outperformed the state-of-art classic ones such as BPG, an image format based on HEVC intra. However, the typical NN codec has high complexity, and it has limited options for parallel data processing. In this work, we propose a conditional separation principle that aims to improve parallelization and lower the computational requirements of an NN codec. We present a Conditional Color Separation (CCS) codec which follows this principle. The color components of an image are split into primary and non-primary ones. The processing of each component is done separately, by jointly trained networks. Our approach allows parallel processing of each component, flexibility to select different channel numbers, and an overall complexity reduction. The CCS codec uses over 40% less memory, has 2x faster encoding and 22% faster decoding speed, with only 4% BD-rate loss in RGB PSNR compared to our baseline model over BPG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_06241 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Learning-Based Conditional Image Coder Using Color Separation Jia, Panqi Koyuncu, Ahmet Burakhan Gaikov, Georgii Karabutov, Alexander Alshina, Elena Kaup, Andre Image and Video Processing Recently, image compression codecs based on Neural Networks(NN) outperformed the state-of-art classic ones such as BPG, an image format based on HEVC intra. However, the typical NN codec has high complexity, and it has limited options for parallel data processing. In this work, we propose a conditional separation principle that aims to improve parallelization and lower the computational requirements of an NN codec. We present a Conditional Color Separation (CCS) codec which follows this principle. The color components of an image are split into primary and non-primary ones. The processing of each component is done separately, by jointly trained networks. Our approach allows parallel processing of each component, flexibility to select different channel numbers, and an overall complexity reduction. The CCS codec uses over 40% less memory, has 2x faster encoding and 22% faster decoding speed, with only 4% BD-rate loss in RGB PSNR compared to our baseline model over BPG. |
| title | Learning-Based Conditional Image Coder Using Color Separation |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2212.06241 |