Deep Lambertian Networks
This work addresses illumination invariance for computer vision tasks like face recognition, but it is incremental as it builds on existing generative models and reflectance assumptions.
The paper tackles illumination variations in visual perception by introducing a multilayer generative model that learns priors over albedo from 2D images, enabling albedo and surface normals estimation from a single image. Experiments show the model generalizes and improves over standard baselines in one-shot face recognition.
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.