Shading Annotations in the Wild
This provides a dataset and method for vision and graphics tasks like intrinsic image decomposition, but it is incremental as it builds on existing data collection and neural network approaches.
The authors tackled the lack of ground truth shading data for real-world images by introducing SAW, a large-scale dataset of shading annotations from crowdsourcing and RGB-D imagery, and used it to train a CNN that reduces artifacts in intrinsic image decomposition.
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/.