Hist2Style：直方图引导的双边网格风格化
Hist2Style: Histogram-Guided Stylization with Bilateral Grids
双边网格上的局部仿射变换可作为高分辨率实时图像编辑的通用算子，配合直方图嵌入实现可解释、可交互的颜色/色调控制，并可用大模型蒸馏出轻量网络，避免生成式幻觉。
原文依据 a bilateral-grid formulation for fast, edge-aware stylization that preserves visual fidelity by constraining operations to locally affine transforms in bilateral space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论照片级真实感风格迁移旨在将输入图像的颜色与色调匹配到风格目标，同时保留原始场景的内容与细节。尽管现有的大型图像模型能够支持此类外观编辑，但其高昂的计算需求、潜在的幻觉生成以及有限的用户控制能力，使其不适合高分辨率、实时的工作流。我们提出 Hist2Style，一种双边网格形式化方法，用于快速、边缘感知的风格化，通过将操作约束为双边空间中的局部仿射变换来保持视觉保真度。我们的模型通过在一个由语言模型与视觉语言模型生成的大规模监督语料上训练，将大型图像编辑模型蒸馏为轻量网络，目标是实现空间变化的颜色编辑。该网络以风格目标的基于直方图的嵌入为条件，从而提供一个可解释的接口，通过修改目标颜色分布来调整输出风格。总体而言，Hist2Style 在构造上保持内容结构、避免幻觉，并支持实时、高分辨率的照片级真实感风格化，以及交互式的用户可控颜色与色调调整。项目页面见 https://dgalor.github.io/hist2style/ 。
英文原文摘要 1321 字符
Photorealistic style transfer aims to match the color and tone of an input image to that of a style target while preserving the content and details of the original scene. Although existing large image models can facilitate these kinds of appearance edits, their high computational demands, potential for hallucinations, and limited user control make them unsuitable for high-resolution, real-time workflows. We introduce Hist2Style, a bilateral-grid formulation for fast, edge-aware stylization that preserves visual fidelity by constraining operations to locally affine transforms in bilateral space. Our model distills a large image editing model into a lightweight network by training on a large supervised corpus generated with language and vision-language models, targeting spatially varying color edits. The network conditions on a histogram-based embedding of the style target to provide an interpretable interface for adjusting the output style by modifying the target color distribution. Overall, Hist2Style maintains content structure by construction, avoids hallucinations, and supports real-time, high-resolution photorealistic stylization with interactive user-controllable color and tone adjustments. Our project page is available at \href https://dgalor.github.io/hist2style/ dgalor.github.io/hist2style/ .