Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction

TL;DR

This paper introduces a novel 6D object pose estimation method that leverages object-specific 3D mesh reconstruction using graph neural networks, improving accuracy and enabling self-validation, outperforming existing methods on standard benchmarks.

Contribution

It presents a new framework that explicitly uses object topological information via mesh reconstruction and differentiable alignment for improved pose estimation.

Findings

Outperforms state-of-the-art on LINEMOD, OCCLUSION, YCB-Video datasets.

Provides a self-validation mechanism for pose accuracy.

Utilizes mesh reconstruction for robust 6D pose estimation.

Abstract

Current 6D object pose methods consist of deep CNN models fully optimized for a single object but with its architecture standardized among objects with different shapes. In contrast to previous works, we explicitly exploit each object's distinct topological information i.e. 3D dense meshes in the pose estimation model, with an automated process and prior to any post-processing refinement stage. In order to achieve this, we propose a learning framework in which a Graph Convolutional Neural Network reconstructs a pose conditioned 3D mesh of the object. A robust estimation of the allocentric orientation is recovered by computing, in a differentiable manner, the Procrustes' alignment between the canonical and reconstructed dense 3D meshes. 6D egocentric pose is then lifted using additional mask and 2D centroid projection estimations. Our method is capable of self validating its pose estimation by measuring the quality of the reconstructed mesh, which is invaluable in real life applications. In our experiments on the LINEMOD, OCCLUSION and YCB-Video benchmarks, the proposed method outperforms state-of-the-arts.