We propose an automatic framework to recover the illumination of indoor scenes based on a single RGB-D image. Unlike previous works, our method can recover spatially varying illumination without using any lighting capturing devices or HDR information. The recovered illumination can produce realistic rendering results. To model the geometry of the visible and invisible parts of scenes corresponding to the input RGB-D image, we assume that all objects shown in the image are located in a box with six faces and build a geometry model based on the depth map. We then present a confidence-scoring based strategy to separate the light sources from the highlight areas. The positions of light sources both in and out of the camera's view are calculated based on the classification result and the recovered geometry model. Finally, an iterative procedure is proposed to calculate the colors of light sources and the materials in the scene. In addition, a data-driven method is used to set constraints on the light source intensities. Using the estimated light sources and geometry model, environment maps at different points in the scene are generated that can model the spatial variance of illumination. The experimental results demonstrate the validity of our approach.

中文翻译：

---

基于单个RGB-D图像的室内场景自动空间变化照明恢复。

我们提出一个自动框架，以基于单个RGB-D图像恢复室内场景的照明。与以前的作品不同，我们的方法无需使用任何照明捕获设备或HDR信息即可恢复空间变化的照明。恢复的照明可以产生逼真的渲染结果。为了对与输入RGB-D图像相对应的场景的可见和不可见部分的几何模型进行建模，我们假定图像中显示的所有对象都位于具有六个面的盒子中，并基于深度图构建几何模型。然后，我们提出一种基于置信度评分的策略，将光源与重点区域分开。根据分类结果和恢复的几何模型，可以计算出摄像机视线内外的光源位置。最后，提出了一种迭代程序来计算光源的颜色和场景中的材质。另外，使用数据驱动的方法来设置对光源强度的约束。使用估计的光源和几何模型，可以生成场景中不同点的环境图，可以对照明的空间变化建模。实验结果证明了该方法的有效性。