Metraipolis › archive › dc_c47263cd5572

LC3EM: Long-Range Context Extrapolation Enhanced Entropy Model for Coordinate-based Overfitting Image Codecs — arXiv:2609.29192

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29192
License (as archived)
CC0-1.0
Archived
2026-10-08T08:56:47.067Z
SHA-256 of the archived text
33a1b0d3a5e3bd9389a51122f3cfff132448966ea33eb0ea64e1f43fe5ef9292
Stable URL of this page
https://metraipolis.com/documento/dc_c47263cd5572

How to cite

LC3EM: Long-Range Context Extrapolation Enhanced Entropy Model for Coordinate-based Overfitting Image Codecs — arXiv:2609.29192 — arXiv (en), https://arxiv.org/abs/2609.29192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c47263cd5572 (Metraipolis archive dc_c47263cd5572, sha256 33a1b0d3a5e3bd9389a51122f3cfff132448966ea33eb0ea64e1f43fe5ef9292)
BibTeX
@misc{dcc47263cd5572,
  title = {LC3EM: Long-Range Context Extrapolation Enhanced Entropy Model for Coordinate-based Overfitting Image Codecs — arXiv:2609.29192},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29192},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c47263cd5572; sha256 33a1b0d3a5e3bd9389a51122f3cfff132448966ea33eb0ea64e1f43fe5ef9292},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coordinate-based overfitting image codecs have attracted increasing attention for their low decoding complexity and independence from cross-image generalization. However, representative approaches such as COOL-CHIC face an inherent entropy-modeling trade-off: lightweight models have limited capacity, while more expressive ones incur additional bitrate overhead from transmitting image-specific parameters. Inspired by the prediction mechanism in traditional codecs, we propose a new entropy-modeling strategy that introduces complementary prediction modes with region-adaptive soft mode selection, rather than relying on a single learned predictor to model diverse types of redundancy. Based on this concept, we develop a Long-Range Context Extrapolation Enhanced Entropy Model (LC3EM), which can be integrated into coordinate-based overfitting codecs. Specifically, a parameter-free Neighborhood-based Linear Extrapolation Mode (NLEM) complements the tiny MLP-based local predictor to exploit long-range contextual redundancy and strongly directional structures. A Minimum-Entropy-Inspired Continuous Mode Selection strategy is designed to adaptively fuse these two complementary modes, while requiring the transmission of only the parameters of a single additional linear layer. Moreover, to alleviate the mismatch between training-time relaxed and actual discrete quantization, we introduce a lightweight iterative latent rounding refinement stage to improve compression performance. Experiments demonstrate consistent improvements across diverse benchmarks, particularly on highly regular computer-generated images. When integrated with COOL-CHIC 4.0, the proposed method achieves BD-rate gains of -3.43\% and -7.69\% on the SIQAD and API datasets, respectively. With COOL-CHIC 5.0 as the backbone, the corresponding gains are -2.88\% and -3.15\%, respectively. The code will be made publicly available soon.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in eess.IV).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.29192 — 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 2026-10-08T08:02:45.513Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).