Intrinsic Images in the Wild
Intrinsic Images in the Wild
复制标题
DOI：
10.1145/2601097.2601206
复制
发表时间：
2014-07-01
影响因子：
6.2
通讯作者：
Snavely, Noah
中科院分区：
文献类型：
--
作者：
Bell, Sean;Bala, Kavita;Snavely, Noah
本征图像分解将图像分为反射层和阴影层。自动的内在图像分解仍然是一个巨大的挑战，特别是对于真实世界的场景。在这个长期存在的问题上，地面真实数据的公开数据集推动了这一问题的进展，例如麻省理工学院的本征图像数据集。然而，获取地面真实数据的困难意味着这样的数据集覆盖的材料和物体范围很小。相比之下，现实世界中的场景包含丰富的形状和材质，由复杂的照明照明。在本文中，我们介绍了一个大规模的公共数据集Intrative Images in the Wild，用于评估室内场景的内在图像分解。我们通过数百万个众包注释创建了这个基准，这些注释是对每个场景中成对的点的材料属性的相对比较。众包使得能够以可扩展的方式获取大型数据库，并利用人类的能力来判断材料的比较，尽管光照不同。在给定我们的数据库的情况下，我们为野外图像开发了一种基于密集CRF的固有图像算法，其性能优于一系列最先进的固有图像算法。内部图像分解仍然是一个具有挑战性的问题；我们公开发布我们的代码和数据库，以支持未来对此问题的研究，
Intrinsic image decomposition separates an image into a reflectance layer and a shading layer. Automatic intrinsic image decomposition remains a significant challenge, particularly for real-world scenes. Advances on this longstanding problem have been spurred by public datasets of ground truth data, such as the MIT Intrinsic Images dataset. However, the difficulty of acquiring ground truth data has meant that such datasets cover a small range of materials and objects. In contrast, real-world scenes contain a rich range of shapes and materials, lit by complex illumination.In this paper we introduce Intrinsic Images in the Wild, a large-scale, public dataset for evaluating intrinsic image decompositions of indoor scenes. We create this benchmark through millions of crowdsourced annotations of relative comparisons of material properties at pairs of points in each scene. Crowdsourcing enables a scalable approach to acquiring a large database, and uses the ability of humans to judge material comparisons, despite variations in illumination. Given our database, we develop a dense CRF-based intrinsic image algorithm for images in the wild that outperforms a range of state-of-the-art intrinsic image algorithms. Intrinsic image decomposition remains a challenging problem; we release our code and database publicly to support future research on this problem,