Single Image Intrinsic Decomposition with Discriminative Feature Encoding
Single Image Intrinsic Decomposition with Discriminative Feature Encoding
复制标题
DOI：
10.1109/iccvw.2019.00531
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Zongji Wang;Feng Lu
中科院分区：
文献类型：
--
作者：
Zongji Wang;Feng Lu
固有图像分解是一个重要的和长期存在的计算机视觉问题。给定单个输入图像，恢复物理场景属性是不适定的。在这项工作中，我们利用深度学习的优势，这被证明是非常有效的解决具有挑战性的计算机视觉问题，包括固有的图像分解。我们的重点在于特征编码阶段，从单个输入图像中提取不同本征层的区分特征。为了实现这一目标，我们探讨了不同的内在成分之间的高维特征嵌入空间的区别特性。我们提出了一个特征发散损失，迫使他们的高维嵌入特征向量被有效地分离。特征分布也被约束以拟合真实的特征分布。此外，我们提供了一种方法来消除MPI Sintel数据集中的数据不一致性，使其更适合于内在图像分解。实验结果表明，所提出的网络结构是能够优于国家的最先进的方法。
Intrinsic image decomposition is an important and long-standing computer vision problem. Given a single input image, recovering the physical scene properties is ill-posed. In this work, we take the advantage of deep learning, which is proven to be highly efficient in solving the challenging computer vision problems including intrinsic image decomposition. Our focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from a single input image. To achieve this goal, we explore the distinctive characteristics between different intrinsic components in the high dimensional feature embedding space. We propose a feature divergence loss to force their high-dimensional embedding feature vectors to be separated efficiently. The feature distributions are also constrained to fit the real ones. In addition, we provide an approach to remove the data inconsistency in the MPI Sintel dataset, making it more proper for intrinsic image decomposition. Experimental results indicate that the proposed network structure is able to outperform the state-of-the-art methods.