Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributions

TL;DR

Corr2Distrib is a novel method that leverages ambiguous correspondences to estimate a comprehensive 6D pose distribution from RGB images, effectively handling symmetries and occlusions.

Contribution

It introduces a symmetry-aware local correspondence representation and a pipeline to generate and refine multiple pose hypotheses into a distribution, outperforming existing methods.

Findings

Outperforms state-of-the-art in pose distribution estimation

Effective in complex non-synthetic scenes

Handles symmetries and occlusions robustly

Abstract

We introduce Corr2Distrib, the first correspondence-based method which estimates a 6D camera pose distribution from an RGB image, explaining the observations. Indeed, symmetries and occlusions introduce visual ambiguities, leading to multiple valid poses. While a few recent methods tackle this problem, they do not rely on local correspondences which, according to the BOP Challenge, are currently the most effective way to estimate a single 6DoF pose solution. Using correspondences to estimate a pose distribution is not straightforward, since ambiguous correspondences induced by visual ambiguities drastically decrease the performance of PnP. With Corr2Distrib, we turn these ambiguities into an advantage to recover all valid poses. Corr2Distrib first learns a symmetry-aware representation for each 3D point on the object's surface, characterized by a descriptor and a local frame. This representation enables the generation of 3DoF rotation hypotheses from single 2D-3D correspondences. Next, we refine these hypotheses into a 6DoF pose distribution using PnP and pose scoring. Our experimental evaluations on complex non-synthetic scenes show that Corr2Distrib outperforms state-of-the-art solutions for both pose distribution estimation and single pose estimation from an RGB image, demonstrating the potential of correspondences-based approaches.