用参考图生成可迁移的胶片模拟效果，无需配对数据或重训练。
Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs
- 从单张参考图预测3D LUT，实现开集胶片风格迁移。
- 颜色阶段达22.05 dB PSNR，全流程1080p下每帧仅5.2毫秒。
- 无需重新训练即可适配未见胶片类型，适合影视后期与创意工作流。
胶片模拟旨在将模拟胶片的视觉风格再现于数字照片。本文针对开集形式——仅需一个参考帧即可匹配任意胶片风格——提出基于参考条件的3D查找表（LUT）方法。传统实时增强通过固定库中的多组3D LUT加权混合实现，但存在门控专家模型中门控坍缩问题：端到端训练后仅激活单一专家，导致K个LUT实际等效于1个。引入熵正则项恢复各专家利用率，提升约1 dB PSNR。然而更深的限制在于：固定基底的LUT是闭集的，训练时即锁定可用风格。因此本文放弃基底，改用从参考图预测残差型3D LUT（StyleLUTNet），通过自监督学习在程序化色彩变换数据上训练。该条件设计消除门控机制，使模型可泛化至未见胶片类型，无需成对数据或重训练。在此色彩主干基础上构建Deep Analog管线，集成基于直方图的色调匹配与物理启发式光学渲染模块——多尺度颗粒与通道独立色晕由逆网络从参考图回归参数驱动。在350个自监督样本上，颜色阶段达到22.05 dB PSNR / 0.925 SSIM，完整流程为21.72 dB / 0.923；1080p下耗时5.2毫秒（192 FPS），并输出兼容主流编辑工具的便携 .cube LUT 文件。此外，条件式LUT训练中出现的残差尺度坍缩问题揭示了通用原则：辅助正则化必须服从重建目标。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。