ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation

TL;DR

This paper introduces ALCN, a meta-learning approach for adaptive contrast normalization that enables robust 3D pose estimation under challenging illumination with minimal training data.

Contribution

The paper presents a novel illumination normalization method using a CNN to adapt normalization parameters, improving 3D pose estimation in low-data scenarios.

Findings

Outperforms standard normalization methods

Effective in challenging lighting conditions

Reduces need for extensive training data

Abstract

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.