Shading Annotations in the Wild

Abstract

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

Unsupervised Deep Single‐Image Intrinsic Decomposition using Illumination‐Varying Image Sequences

“…While several metrics [13,3,18] have been suggested to evaluate IID, it has been observed that none give the full picture [18]. Therefore, we now assemble and extend a set of metrics that covers many requirements of IID algorithms, i.e.…”

“…Shading Annotations in the Wild [18] (SAW) extends and complements IIW [3] with partly dense shading annotations by humans, who were asked to classify pixels as belonging to either smooth shadow areas or non-smooth shadow boundaries. It is taken as a semi-dense GT reference to measure the SAW quality of SIID algorithms applied on the SAW dataset.…”

CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering

“…We conduct experiments on two datasets of real world scenes, IIW [5] and SAW [6] (using test data unseen during training) and compare our method with several state-ofthe-art intrinsic images algorithms. Additionally, we also evaluate the generalization of our CGI dataset by evaluating it on the MIT Intrinsic Images benchmark [35].…”

“…SAW also provides individual point annotations at cast shadow boundaries. As noted in [6], these points are not localized precisely on shadow boundaries, and so we apply a morphological dilation with a radius of 5 pixels to the set of marked points before using them in training. This results in shadow boundary regions.…”

“…To evaluate our shading predictions, we test our models on the SAW [6] test set, utilizing the error metric introduced in [28]. We also propose a new, more challenging error metric for SAW evaluation.…”