Shading Annotations in the Wild
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017)
摘要
Understanding shading effects in images is critical for a variety of vision and graphics problems, including intrinsic image decomposition, shadow removal, image relighting, and inverse rendering. As is the case with other vision tasks, machine learning is a promising approach to understanding shading - but there is little ground truth shading data available for real-world images. We introduce Shading Annotations in the Wild (SAW), a new large-scale, public dataset of shading annotations in indoor scenes, comprised of multiple forms of shading judgments obtained via crowdsourcing, along with shading annotations automatically generated from RGB-D imagery. We use this data to train a convolutional neural network to predict per-pixel shading information in an image. We demonstrate the value of our data and network in an application to intrinsic images, where we can reduce decomposition artifacts produced by existing algorithms. Our database is available at http://opensurfaces.cs.cornell.edu/saw.
更多查看译文
关键词
graphics problems,intrinsic image decomposition,shadow removal,image relighting,inverse rendering,vision tasks,machine learning,Shading Annotations in the Wild,indoor scenes,RGB-D imagery,convolutional neural network training,per-pixel shading information prediction,decomposition artifacts reduction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络