Log In Sign Up

Deep Lambertian Networks

by   Yichuan Tang, et al.

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.


page 5

page 6

page 7

page 8


Improving Shadow Suppression for Illumination Robust Face Recognition

2D face analysis techniques, such as face landmarking, face recognition ...

GMLight: Lighting Estimation via Geometric Distribution Approximation

Lighting estimation from a single image is an essential yet challenging ...

Complex-Object Visual Inspection via Multiple Lighting Configurations

The design of an automatic visual inspection system is usually performed...

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

Face verification remains a challenging problem in very complex conditio...

Illumination-Invariant Image from 4-Channel Images: The Effect of Near-Infrared Data in Shadow Removal

Removing the effect of illumination variation in images has been proved ...

What's In A Patch, I: Tensors, Differential Geometry and Statistical Shading Analysis

We develop a linear algebraic framework for the shape-from-shading probl...