Metraipolis › archive › dc_5ae9030524da
Multi-scale Image Representation Compression — arXiv:2609.04274
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04274
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T23:44:10.471Z
- SHA-256 of the archived text
d7353ef6ba8e9a355478319f3d5d2d0a7c2b63247806f146df3fbb275e5e8178- Stable URL of this page
https://metraipolis.com/documento/dc_5ae9030524da
How to cite
Multi-scale Image Representation Compression — arXiv:2609.04274 — arXiv (en), https://arxiv.org/abs/2609.04274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ae9030524da (Metraipolis archive dc_5ae9030524da, sha256 d7353ef6ba8e9a355478319f3d5d2d0a7c2b63247806f146df3fbb275e5e8178)
BibTeX
@misc{dc5ae9030524da,
title = {Multi-scale Image Representation Compression — arXiv:2609.04274},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04274},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ae9030524da; sha256 d7353ef6ba8e9a355478319f3d5d2d0a7c2b63247806f146df3fbb275e5e8178},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at the cost of a longer overfitting process. However, these overfitted image codecs are not fully optimized toward the rate-distortion objective: their network weights remain in full precision during training, and the associated quantization parameters are selected in a separate post-training stage. Furthermore, their synthesis operates at a single scale, which overlooks cross-scale redundancy. In this paper, we propose MIRC, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC. We further introduce a multi-scale representation with cross-stage parameter sharing, which improves coding efficiency at a small transmitted overhead. On the CLIC2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0). Moreover, MIRC offers a family of configurations spanning 1.2 to 2.9 kMAC per pixel, so the decoding budget can be selected to match the deployment target. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV). Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2609.04274 — 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 2026-10-16T23:16:11.477Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).