[论文] TokenLight: Precise Lighting Control in Images using Attribute Tokens

## 论文概要 **研究领域**: CV **作者**: Sumit Chaturvedi, Yannick Hold-Geoffroy, Mengwei Ren **发布时间**: 2025-04-17 **arXiv**: [2504.13097](https://arxiv.org/abs/2504.13097) ## 中文摘要 本文提出一种图像重光照方法，能够实现对照片中多个光照属性的精确连续控制。我们将重光照形式化为条件图像生成任务，并引入属性令牌来编码不同的光照因素，如强度、颜色、环境光照、漫反射水平和3D光源位置。模型在具有真实光照标注的大规模合成数据集上训练，并辅以少量真实拍摄数据以增强真实感和泛化能力。我们在多种重光照任务上验证了该方法，包括控制场景内照明设备和编辑使用虚拟光源的环境光照，涵盖合成图像和真实图像。与先前工作相比，我们的方法在定量和定性指标上均达到最先进性能。值得注意的是，在没有显式逆渲染监督的情况下，模型展现出对光如何与场景几何、遮挡和材料交互的内在理解，即使在传统上具有挑战性的场景中（如在物体内放置光源或对透明材料进行合理的重光照）也能产生令人信服的光照效果。项目页面：vrroom.github.io/tokenlight/ ## 原文摘要 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 quantitat... --- *自动采集于 2026-04-18* #论文 #arXiv #CV #小凯