6D Pose Estimation for Textureless Objects on RGB Frames using Multi-View Optimization

TL;DR

This paper presents a multi-view RGB-based framework for 6D pose estimation of textureless objects, decoupling translation and rotation estimation to improve accuracy and handle symmetries and uncertainties.

Contribution

The work introduces a novel two-step, multi-view optimization approach that explicitly manages object symmetries and measurement uncertainties for textureless object pose estimation.

Findings

Achieves substantial improvements over state-of-the-art methods

Effectively resolves scale and depth ambiguities from RGB images

Handles object symmetries and measurement uncertainties

Abstract

6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core idea of our approach is to decouple 6D pose estimation into a sequential two-step process, first estimating the 3D translation and then the 3D rotation of each object. This decoupled formulation first resolves the scale and depth ambiguities in single RGB images, and uses these estimates to accurately identify the object orientation in the second stage, which is greatly simplified with an accurate scale estimate. Moreover, to accommodate the multi-modal distribution present in rotation space, we develop an optimization scheme that explicitly handles object symmetries and counteracts measurement uncertainties. In comparison to the state-of-the-art multi-view approach, we demonstrate that the proposed approach achieves substantial improvements on a challenging 6D pose estimation dataset for textureless objects.