Metraipolis › archive › dc_db7a92199b13

Neural Image Compression with Internal-External Prior Fusion and Alignment — arXiv:2611.07644

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07644
License (as archived)
CC0-1.0
Archived
2026-11-06T14:42:31.036Z
SHA-256 of the archived text
36f636d75cd77ab7ba60315d2e932a987038239edc3e3965e593ddef6ec06b43
Stable URL of this page
https://metraipolis.com/documento/dc_db7a92199b13

How to cite

Neural Image Compression with Internal-External Prior Fusion and Alignment — arXiv:2611.07644 — arXiv (en), https://arxiv.org/abs/2611.07644 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db7a92199b13 (Metraipolis archive dc_db7a92199b13, sha256 36f636d75cd77ab7ba60315d2e932a987038239edc3e3965e593ddef6ec06b43)
BibTeX
@misc{dcdb7a92199b13,
  title = {Neural Image Compression with Internal-External Prior Fusion and Alignment — arXiv:2611.07644},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07644},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db7a92199b13; sha256 36f636d75cd77ab7ba60315d2e932a987038239edc3e3965e593ddef6ec06b43},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07644. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing context models for learned image com- pression rely primarily on internal priors from the current image, overlooking common patterns and typical textures shared across natural images. To address this limitation, we propose an Internal-External Prior Fusion-Alignment (IE-PFA) context model built upon quadtree spatial-channel joint modeling, where a learnable dictionary shared by the encoder and decoder serves as an external prior. Specifically, an RWKV-based Spatial- Channel Prior Fusion (RSCPF) module efficiently fuses inter- nal and external priors along spatial and channel dimensions with linear complexity, while a training-only Self-Distilled Prior Alignment (SDPA) mechanism aligns them without inference overhead. Moreover, our model supports variable-rate coding over 64 quality levels within a single network and is accelerated by custom CUDA operators. Experiments on seven benchmarks demonstrate state-of-the-art rate-distortion performance, achiev- ing an average BD-Rate saving of 21.65% over VTM-22.0-Intra, with only 29.9M parameters and the fastest coding speed among advanced neural codecs (61 ms encoding and 52 ms decoding). Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07644 — 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 2026-11-06T14:18:42.682Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).