论文标题
签名：通过语义和不变的梯度驱动网络用于室内场景的固有图像分解
SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes
论文作者
论文摘要
固有图像分解（IID）是一个不受限制的问题。因此，传统方法使用手工制作的先验来限制问题。但是，在应对复杂场景时，这些约束受到限制。深度学习的方法通过数据隐含地学习了这些约束，但是它们通常会遭受数据集偏见的困扰（由于无法包括所有可能的成像条件）。 在本文中，提出了两者的组合。利用语义和不变特征（例如语义和不变特征）以获得语义和物理上合理的反射率转换。这些过渡用于引导具有隐式同质性约束的进行性CNN，以分解反射率和阴影图。 进行了一项消融研究，表明拟议的先验和进行性CNN的使用增加了IID的性能。我们提出的数据集和标准现实世界IIW数据集的最新性能都显示了所提出的方法的有效性。代码可在https://github.com/morpheus3000/signet上提供
Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep learning-based approaches learn these constraints implicitly through the data, but they often suffer from dataset biases (due to not being able to include all possible imaging conditions). In this paper, a combination of the two is proposed. Component specific priors like semantics and invariant features are exploited to obtain semantically and physically plausible reflectance transitions. These transitions are used to steer a progressive CNN with implicit homogeneity constraints to decompose reflectance and shading maps. An ablation study is conducted showing that the use of the proposed priors and progressive CNN increase the IID performance. State of the art performance on both our proposed dataset and the standard real-world IIW dataset shows the effectiveness of the proposed method. Code is made available at https://github.com/Morpheus3000/SIGNet
