Shading Annotations in the Wild

By Balazs Kovacs, Sean Bell, Noah Snavely, Kavita Bala. 2017

71 citations recorded by the source corpus.

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.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

1. Zhengqi Li
2. Nathan Paczan
3. Mike Roberts
4. Noah Snavely
5. Jonathan T. Barron
6. Kalyan Sunkavalli
7. Zexiang Xu
8. Jia-Bin Huang

In Computer Vision and Pattern Recognition

1. Zhengqi Li
2. Noah Snavely
3. Nathan Paczan
4. Mike Roberts
5. Jitendra Malik
6. Luc Van Gool
7. Jia-Bin Huang
8. Jiashi Feng

In Evaluation & Benchmarks

1. Zhengqi Li
2. Noah Snavely
3. Nathan Paczan
4. Mike Roberts
5. Amir Zamir
6. Roman Bachmann

Citations in the corpus

• Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, background): “Together, these features make our dataset well-suited for geometric learning problems that require direct 3D supervision (e.g., [27]), multi-task learning problems that require reasoning jointly over multiple input and output modalities (e.g., [71]), and inverse rendering problems (e.g., [13, 40]).”
• CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering (2018, methodology): “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.”