Deep Lambertian Networks

TL;DR

This paper introduces a deep generative model combining Deep Belief Nets and Lambertian reflectance to estimate illumination-invariant features like albedo and surface normals, improving face recognition under varying lighting conditions.

Contribution

It presents a novel multilayer generative model that learns priors over albedo and surface normals, enabling illumination-invariant recognition from a single image.

Findings

Model generalizes well to unseen lighting conditions.

Improves one-shot face recognition accuracy.

Learns meaningful priors over surface properties.

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.