Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression

Abstract

We introduce a new approach to intrinsic image decomposition, the task of decomposing a single image into albedo and shading components. Our strategy, which we term direct intrinsics, is to learn a convolutional neural network (CNN) that directly predicts output albedo and shading channels from an input RGB image patch. Direct intrinsics is a departure from classical techniques for intrinsic image decomposition, which typically rely on physically-motivated priors and graph-based inference algorithms. The large-scale synthetic ground-truth of the MPI Sintel dataset plays a key role in training direct intrinsics. We demonstrate results on both the synthetic images of Sintel and the real images of the classic MIT intrinsic image dataset. On Sintel, direct intrinsics, using only RGB input, outperforms all prior work, including methods that rely on RGB+Depth input. Direct intrinsics also generalizes across modalities; it produces quite reasonable decompositions on the real images of the MIT dataset. Our results indicate that the marriage of CNNs with synthetic training data may be a powerful new technique for tackling classic problems in computer vision.

International Conference on Computer Vision (ICCV), 2015

Cited by in corpus (17)

• Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
• Self-Supervised Intrinsic Image Decomposition
• Learning Intrinsic Image Decomposition from Watching the World
• Inverse Transport Networks
• Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition
• InverseRenderNet: Learning single image inverse rendering
• Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation
• Semantic Hierarchical Priors for Intrinsic Image Decomposition
• What Is Around The Camera?
• Deep Reflectance Maps
• Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
• Single-image Tomography: 3D Volumes from 2D Cranial X-Rays
• Plausible Shading Decomposition For Layered Photo Retouching
• Reflectance Adaptive Filtering Improves Intrinsic Image Estimation
• Fast Fourier Intrinsic Network
• Authoring image decompositions with generative models
• Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image Sequences