ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation
This addresses the challenge of illumination robustness in 3D pose estimation for specific objects, offering a solution where collecting diverse training data is difficult, though it is incremental as it builds on existing normalization methods.
The paper tackles the problem of robust 3D pose estimation under varying illumination by proposing a meta-learning-based contrast normalization method that adapts to input images, enabling accurate detection from few training samples and outperforming standard normalization techniques.
To be robust to illumination changes when detecting objects in images, the current trend is to train a Deep Network with training images captured under many different lighting conditions. Unfortunately, creating such a training set is very cumbersome, or sometimes even impossible, for some applications such as 3D pose estimation of specific objects, which is the application we focus on in this paper. We therefore propose a novel illumination normalization method that lets us learn to detect objects and estimate their 3D pose under challenging illumination conditions from very few training samples. Our key insight is that normalization parameters should adapt to the input image. In particular, we realized this via a Convolutional Neural Network trained to predict the parameters of a generalization of the Difference-of-Gaussians method. We show that our method significantly outperforms standard normalization methods and demonstrate it on two challenging 3D detection and pose estimation problems.