Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences

TL;DR

This paper introduces Alignist, a novel method for estimating object pose distributions in robotics by integrating CAD model shape and correspondence information, enabling faster convergence and sharper distribution learning compared to contrastive learning methods.

Contribution

Alignist leverages CAD-informed shape and correspondence data to improve pose distribution estimation, reducing training data requirements and enhancing distribution sharpness.

Findings

Achieves better distribution sharpness and convergence speed.

Outperforms contrastive learning approaches on SYMSOL-I and T-Less datasets.

Effectively utilizes CAD priors for pose distribution estimation.

Abstract

Object pose distribution estimation is crucial in robotics for better path planning and handling of symmetric objects. Recent distribution estimation approaches employ contrastive learning-based approaches by maximizing the likelihood of a single pose estimate in the absence of a CAD model. We propose a pose distribution estimation method leveraging symmetry respecting correspondence distributions and shape information obtained using a CAD model. Contrastive learning-based approaches require an exhaustive amount of training images from different viewpoints to learn the distribution properly, which is not possible in realistic scenarios. Instead, we propose a pipeline that can leverage correspondence distributions and shape information from the CAD model, which are later used to learn pose distributions. Besides, having access to pose distribution based on correspondences before learning pose distributions conditioned on images, can help formulate the loss between distributions. The prior knowledge of distribution also helps the network to focus on getting sharper modes instead. With the CAD prior, our approach converges much faster and learns distribution better by focusing on learning sharper distribution near all the valid modes, unlike contrastive approaches, which focus on a single mode at a time. We achieve benchmark results on SYMSOL-I and T-Less datasets.