发表机构
Tianjin University; KlingAI Research; Deva Research（天津大学; KlingAI研究院; Deva研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有图像重光照方法无法在手绘涂鸦输入与结果间建立有效映射的问题，提出材料解耦光照表示Lumi Map，构建Dior-Light方法，提升了重光照精度与光照控制能力。
AI 中文摘要
可控图像重光照是图像编辑中的重要问题，手绘涂鸦为指定所需光照提供了直观界面。但现有方法未在涂鸦输入与重光照结果间建立一致有效的映射，限制了对光照强度、色度及复杂空间分布的控制能力。为解决此局限，我们引入名为Lumi Map的材料解耦光照表示，在用户涂鸦与生成光照间建立显式映射，提升重光照精度与可控性。具体而言，我们使用渲染器合成源图像-Lumi Map-重光照图像三元组，训练模型以Lumi Map为条件预测目标重光照结果；为缓解合成数据引入的域差距，我们进一步对真实重光照对执行重建训练，提升模型对真实世界图像的泛化能力。最终，我们提出由手绘笔触控制的图像重光照方法Dior-Light。大量实验表明，我们的方法在重光照精度上优于现有方法，且能对野外图像实现光照强度与色度的有效控制。
英文摘要
Controllable image relighting is an important problem in image editing, and hand-drawn scribbles provide an intuitive interface for specifying the desired illumination. However, existing methods do not establish a consistent and effective mapping between scribble inputs and relighting results, limiting their ability to control illumination intensity, chromaticity, and complex spatial distributions. We address this limitation by introducing a material-decoupled illumination representation, termed the Lumi Map, which establishes an explicit mapping between user scribbles and the resulting illumination, thereby improving both relighting accuracy and controllability. Specifically, we use a renderer to synthesize source image-Lumi Map-relit image triplets and train the model to predict the target relighting result conditioned on the Lumi Map. To mitigate the domain gap introduced by synthetic data, we further perform reconstruction training on real relighting pairs, improving the model's generalization to real-world images. Finally, we present Dior-Light, an image relighting method controlled by hand-drawn strokes. Extensive experiments demonstrate that our method outperforms existing approaches in relighting accuracy and enables effective control over illumination intensity and chromaticity on in-the-wild images.
