Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909366007889920 |
|---|---|
| author | Liu, Zhening Zhang, Xinjie Shao, Jiawei Lin, Zehong Zhang, Jun |
| author_facet | Liu, Zhening Zhang, Xinjie Shao, Jiawei Lin, Zehong Zhang, Jun |
| contents | With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the compression of one view is dependent on the other, resulting in imbalanced compression. To address this issue, we introduce a symmetric bidirectional stereo image compression architecture, named BiSIC. Specifically, we propose a 3D convolution based codec backbone to capture local features and incorporate bidirectional attention blocks to exploit global features. Moreover, we design a novel cross-dimensional entropy model that integrates various conditioning factors, including the spatial context, channel context, and stereo dependency, to effectively estimate the distribution of latent representations for entropy coding. Extensive experiments demonstrate that our proposed BiSIC outperforms conventional image/video compression standards, as well as state-of-the-art learning-based methods, in terms of both PSNR and MS-SSIM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10632 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model Liu, Zhening Zhang, Xinjie Shao, Jiawei Lin, Zehong Zhang, Jun Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the compression of one view is dependent on the other, resulting in imbalanced compression. To address this issue, we introduce a symmetric bidirectional stereo image compression architecture, named BiSIC. Specifically, we propose a 3D convolution based codec backbone to capture local features and incorporate bidirectional attention blocks to exploit global features. Moreover, we design a novel cross-dimensional entropy model that integrates various conditioning factors, including the spatial context, channel context, and stereo dependency, to effectively estimate the distribution of latent representations for entropy coding. Extensive experiments demonstrate that our proposed BiSIC outperforms conventional image/video compression standards, as well as state-of-the-art learning-based methods, in terms of both PSNR and MS-SSIM. |
| title | Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.10632 |