Metraipolis › archive › dc_22edd513044f

Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs — arXiv:2608.14702

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14702
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:54.687Z
SHA-256 of the archived text
6b0a3446c2996e673e78a6f77b5c852dd2413f58c12ec22e8b1cb5421b624b65
Stable URL of this page
https://metraipolis.com/documento/dc_22edd513044f

How to cite

Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs — arXiv:2608.14702 — arXiv (en), https://arxiv.org/abs/2608.14702 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22edd513044f (Metraipolis archive dc_22edd513044f, sha256 6b0a3446c2996e673e78a6f77b5c852dd2413f58c12ec22e8b1cb5421b624b65)
BibTeX
@misc{dc22edd513044f,
  title = {Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs — arXiv:2608.14702},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14702},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22edd513044f; sha256 6b0a3446c2996e673e78a6f77b5c852dd2413f58c12ec22e8b1cb5421b624b65},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14702. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form -- matching any reference film frame from a single example -- with a 3D lookup table (LUT) predicted from that reference. Real-time image enhancement predicts per-image weights over a fixed bank of 3D LUTs and blends them. We show this is a gated mixture of experts and inherits its failure: trained end-to-end against reconstruction, the gate collapses onto a single expert, so a bank of K LUTs delivers the capacity of one. An entropy term, the enhancement-setting analogue of mixture-of-experts load balancing, restores utilization and recovers about 1 dB PSNR. The deeper constraint survives: a fixed LUT basis is closed-set, freezing the achievable looks at training time. We therefore discard the basis and predict a single 3D LUT as a residual from a reference image (StyleLUTNet), trained by self-supervision on procedurally generated color transforms. The conditional design removes the gate and generalizes open-set to unseen film stocks without paired data or retraining. Around this color backbone we build Deep Analog, a film-emulation pipeline that adds histogram-based tone matching and a physics-informed optical renderer -- multi-scale grain and per-channel halation driven by parameters an inverse network regresses from the reference. On 350 self-supervised pairs the color stage reaches 22.05 dB PSNR / 0.925 SSIM and the full pipeline 21.72 dB / 0.923; the color path runs in 5.2 ms at 1080p (192 FPS) and exports a portable .cube LUT for standard editing tools. A second degeneracy in conditional LUT training -- residual-scale collapse -- shares the root cause and yields a general principle: auxiliary regularization must stay subordinate to reconstruction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Machine Learning (cs.LG); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.14702 — 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 2026-10-18T19:02:44.214Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).