Metraipolis › archive › dc_b9ac977ea7ff

Multiple Scale Latents for Learned Image Compression — arXiv:2608.10952

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10952
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:33.928Z
SHA-256 of the archived text
f3e55ed30d9a41a91b07df7c835af87ab3e08899341ba571e34180aa7f66ca69
Stable URL of this page
https://metraipolis.com/documento/dc_b9ac977ea7ff

How to cite

Multiple Scale Latents for Learned Image Compression — arXiv:2608.10952 — arXiv (en), https://arxiv.org/abs/2608.10952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9ac977ea7ff (Metraipolis archive dc_b9ac977ea7ff, sha256 f3e55ed30d9a41a91b07df7c835af87ab3e08899341ba571e34180aa7f66ca69)
BibTeX
@misc{dcb9ac977ea7ff,
  title = {Multiple Scale Latents for Learned Image Compression — arXiv:2608.10952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9ac977ea7ff; sha256 f3e55ed30d9a41a91b07df7c835af87ab3e08899341ba571e34180aa7f66ca69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most learned image compression systems rely on a single latent representation combined with a hyperprior, which limits their ability to efficiently capture image structure across spatial scales. In this work, we propose a hierarchical latent representation to improve the efficiency of the entropy model. By using multiple latents at different scales, each with its own entropy model, we better capture the spatial structure of the latent representation. Our experiments show that this approach achieves a 17.9% BD-rate reduction over VVC on Kodak, demonstrating the effectiveness of multi-scale latent representations. Furthermore, the approach is orthogonal to other advances in learned image compression, making it a versatile addition to existing methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10952 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:25:27.302Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).