Deep Lambertian Networks

Abstract

Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it for recognition. The object albedo and surface normals are examples of such representations. In this paper, we introduce a multilayer generative model where the latent variables include the albedo, surface normals, and the light source. Combining Deep Belief Nets with the Lambertian reflectance assumption, our model can learn good priors over the albedo from 2D images. Illumination variations can be explained by changing only the lighting latent variable in our model. By transferring learned knowledge from similar objects, albedo and surface normals estimation from a single image is possible in our model. Experiments demonstrate that our model is able to generalize as well as improve over standard baselines in one-shot face recognition.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

Cited by in corpus (17)

• Deep Convolutional Inverse Graphics Network
• Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
• Self-Supervised Intrinsic Image Decomposition
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling
• Inverse Transport Networks
• A CNN Based Approach for the Point-Light Photometric Stereo Problem
• DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
• Deep video gesture recognition using illumination invariants
• Disentangled Representations in Neural Models
• Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
• Consensus Message Passing for Layered Graphical Models
• Deep Reflectance Maps
• Critical Contours: An Invariant Linking Image Flow with Salient Surface Organization
• Learning to Separate Multiple Illuminants in a Single Image
• Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search
• Adaptive Multiscale Illumination-Invariant Feature Representation for Undersampled Face Recognition