Multiscale Augmented Normalizing Flows for Image Compression
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916256050839552 |
|---|---|
| author | Windsheimer, Marc Brand, Fabian Kaup, André |
| author_facet | Windsheimer, Marc Brand, Fabian Kaup, André |
| contents | Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of the encoding transform. This issue can be resolved by using invertible latent variable models, which allow a perfect reconstruction if no quantization is performed. Furthermore, many traditional image and video coders apply dynamic block partitioning to vary the compression of certain image regions depending on their content. Inspired by this approach, hierarchical latent spaces have been applied to learning-based compression networks. In this paper, we present a novel concept, which adapts the hierarchical latent space for augmented normalizing flows, an invertible latent variable model. Our best performing model achieved average rate savings of more than 7% over comparable single-scale models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_05451 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multiscale Augmented Normalizing Flows for Image Compression Windsheimer, Marc Brand, Fabian Kaup, André Image and Video Processing Computer Vision and Pattern Recognition Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of the encoding transform. This issue can be resolved by using invertible latent variable models, which allow a perfect reconstruction if no quantization is performed. Furthermore, many traditional image and video coders apply dynamic block partitioning to vary the compression of certain image regions depending on their content. Inspired by this approach, hierarchical latent spaces have been applied to learning-based compression networks. In this paper, we present a novel concept, which adapts the hierarchical latent space for augmented normalizing flows, an invertible latent variable model. Our best performing model achieved average rate savings of more than 7% over comparable single-scale models. |
| title | Multiscale Augmented Normalizing Flows for Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2305.05451 |