InstantRetouch：基于双边空间的高效高保真指令引导图像修饰
InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
用低分辨率双边网格预测仿射变换替代像素/潜变量编辑，把多步扩散模型通过变分分数蒸馏蒸馏进该框架，为视觉研究者提供了一条兼顾保真度与延迟的指令引导编辑路径，可直接迁移到其他需要内容解耦的局部调整任务。
原文依据 our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论语言引导的照片修饰旨在调整色彩与色调，同时保持几何结构与纹理不变。近期，基于扩散模型的修饰方法展现出更优的视觉质量，但受其生成式本质所限常面临保真度问题，且因迭代采样过程而效率不足。本文提出一种高效且保真的修饰方法，采用双边空间操作，该表示既紧凑又与内容解耦。具体而言，我们的模型不直接编辑像素或图像潜变量，而是预测一个低分辨率的仿射变换双边网格，该网格通过学习到的引导图进行切片，再应用于全分辨率图像。这一做法同时带来高保真度与效率提升。为保留预训练生成模型的强先验，我们利用变分分数蒸馏将多步扩散模型蒸馏进双边网格框架，并辅以提示词对齐损失以引导指令遵循行为。此外，我们引入一个新的基准，并从保真度、指令遵循与效率多个维度评估我们的方法。与最新的修饰方法（如 Gemini-2.5-Flash（Nano-Banana））相比，我们的方法能够避免内容漂移、显著改善延迟，并生成视觉上令人满意的编辑结果，同时保持高水平的保真度。
英文原文摘要 1381 字符
Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process.In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled. Specifically, instead of directly editing pixels or image latents, our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map and then applied to the full-resolution image. This approach yields both high fidelity and improved efficiency.To retain strong priors of a pretrained generative model, we distill a multi-step diffusion model into our bilateral grid framework using Variational Score Distillation, complemented by a prompt alignment loss to guide instruction-following behavior. Additionally, we introduce a new benchmark and evaluate our method across multiple dimensions: fidelity, instruction following, and efficiency.Compared to the latest retouch methods, like Gemini-2.5-Flash (Nano-Banana), our method can avoid content drift, significantly improve latency, and generate visually pleasing edits, while maintaining a high level of fidelity.