TokenLight：使用属性 token 实现图像中的精确光照控制
TokenLight: Precise Lighting Control in Images using Attribute Tokens
把光照属性（强度、颜色、环境光、漫反射程度、3D 光源位置）拆成独立 token 做条件控制，为图像编辑类工作提供了「属性解耦 + 连续可调」的条件注入范式，可直接迁移到材质、阴影、色温等其他连续编辑维度。
原文依据 we introduce attribute tokens to encode distinct lighting factors such as intensity, color, ambient illumination, diffuse level, and 3D light positions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出一种图像重打光方法，可对照片中的多种光照属性实现精确且连续的控制。我们将重打光建模为条件图像生成任务，并引入属性 token 来编码强度、颜色、环境光、漫反射程度以及 3D 光源位置等不同的光照因素。模型在大规模合成数据集上训练，该数据集带有真实光照标注，并辅以少量真实拍摄数据以提升真实感与泛化能力。我们在合成图像与真实图像上验证了该方法在多种重打光任务中的表现，包括控制场景内灯具以及使用虚拟光源编辑环境光照。与先前工作相比，本方法在定量与定性上均达到最优性能。值得注意的是，在没有显式逆渲染监督的情况下，模型仍表现出对光照如何与场景几何、遮挡和材质相互作用的内在理解，即使在将光源置于物体内部或对透明材质进行重打光等传统上具有挑战性的场景中，也能生成令人信服的光照效果。
英文原文摘要 1196 字符
This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to encode distinct lighting factors such as intensity, color, ambient illumination, diffuse level, and 3D light positions. The model is trained on a large-scale synthetic dataset with ground-truth lighting annotations, supplemented by a small set of real captures to enhance realism and generalization. We validate our approach across a variety of relighting tasks, including controlling in-scene lighting fixtures and editing environment illumination using virtual light sources, on synthetic and real images. Our method achieves state-of-the-art quantitative and qualitative performance compared to prior work. Remarkably, without explicit inverse rendering supervision, the model exhibits an inherent understanding of how light interacts with scene geometry, occlusion, and materials, yielding convincing lighting effects even in traditionally challenging scenarios such as placing lights within objects or relighting transparent materials plausibly.