Intrinsic image decomposition, i.e. , decomposing a natural image into a reflectance image and a shading image, is used in many augmented reality applications for achieving better visual coherence between virtual contents and real scenes. The main challenge is that the decomposition is ill-posed, especially in indoor scenes where lighting conditions are complicated, while real training data is inadequate. To solve this challenge, we propose NIID-Net, a novel learning-based framework that adapts surface normal knowledge for improving the decomposition. The knowledge learned from relatively more abundant data for surface normal estimation is integrated into intrinsic image decomposition in two novel ways. First, normal feature adapters are proposed to incorporate scene geometry features when decomposing the image. Secondly, a map of integrated lighting is proposed for propagating object contour and planarity information during shading rendering. Furthermore, this map is capable of representing spatially-varying lighting conditions indoors. Experiments show that NIID-Net achieves competitive performance in reflectance estimation and outperforms all previous methods in shading estimation quantitatively and qualitatively. The source code of our implementation is released at https://github.com/zju3dv/NIID-Net .

中文翻译：

---

NIID-Net：调整表面常识以用于室内场景中的固有图像分解。

固有图像分解 即 将自然图像分解为反射图像和阴影图像的方法被用于许多增强现实应用程序中，以实现虚拟内容与真实场景之间更好的视觉连贯性。主要挑战是分解不适当，尤其是在照明条件复杂的室内场景中，而实际训练数据却不足。为了解决这一挑战，我们提出了NIID-Net，这是一个新颖的基于学习的框架，该框架适应了表面法线知识以改善分解。从相对丰富的数据中获取的用于表面法线估计的知识可以通过两种新颖的方式集成到固有图像分解中。首先，在分解图像时，建议使用常规特征适配器以包含场景几何特征。其次，提出了一个集成照明图，用于在着色渲染期间传播对象轮廓和平面度信息。此外，该地图能够表示室内空间变化的照明条件。实验表明，NIID-Net在反射率估计方面具有竞争优势，并且在定量和定性方面都优于所有以前的阴影估计方法。我们的实现的源代码发布于https://github.com/zju3dv/NIID-Net 。