Metraipolis › archive › dc_bcca95ef5cfd
Efficient JPEG Restoration in the Wavelet Domain via Mean Flows — arXiv:2608.28730
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28730
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:56.042Z
- SHA-256 of the archived text
4afea384c5751b51483b9aeb88eb3e812d156d335d3487e0b69fcec9f18c7df0- Stable URL of this page
https://metraipolis.com/documento/dc_bcca95ef5cfd
How to cite
Efficient JPEG Restoration in the Wavelet Domain via Mean Flows — arXiv:2608.28730 — arXiv (en), https://arxiv.org/abs/2608.28730 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcca95ef5cfd (Metraipolis archive dc_bcca95ef5cfd, sha256 4afea384c5751b51483b9aeb88eb3e812d156d335d3487e0b69fcec9f18c7df0)
BibTeX
@misc{dcbcca95ef5cfd,
title = {Efficient JPEG Restoration in the Wavelet Domain via Mean Flows — arXiv:2608.28730},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28730},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcca95ef5cfd; sha256 4afea384c5751b51483b9aeb88eb3e812d156d335d3487e0b69fcec9f18c7df0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28730. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment. We present a 65M-parameter generative restorer that attains the lowest LPIPS at QF 10 and 20 on LIVE-1, Urban100, and DIV2K-val while sustaining 8.05 images/s at $1024\times1024$ on a single RTX 3090, roughly $4.9\times$ the reported throughput of one-step SODiff at one-twentieth of its parameters. Trained from scratch, the model replaces the learned VAE encoder-decoder with an exactly invertible two-level Haar transform, predicts a clean wavelet-domain residual through a rank-enhanced linear-attention DiT that estimates compression severity internally, and is optimized with an improved MeanFlow objective that enables inference in one or two network evaluations without distillation. Large pretrained priors remain stronger under severe compression (QF 5), whereas our model prioritizes throughput for deployment-constrained restoration. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28730 — 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 2026-10-17T09:28:48.248Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).