Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation

TL;DR

This paper introduces SymCode and SymNet, a symmetry-aware approach for 6D object pose estimation that effectively handles symmetric objects by using one-to-many correspondences, resulting in faster and accurate pose predictions.

Contribution

The paper proposes SymCode and SymNet, novel symmetry-aware encoding and a direct regression network that improve pose estimation for symmetric objects without PnP solving.

Findings

Faster runtime compared to existing methods

Achieves comparable accuracy on T-LESS and IC-BIN benchmarks

Effectively resolves symmetry ambiguity in pose estimation

Abstract

Estimating the 6D pose of an object from a single RGB image is a critical task that becomes additionally challenging when dealing with symmetric objects. Recent approaches typically establish one-to-one correspondences between image pixels and 3D object surface vertices. However, the utilization of one-to-one correspondences introduces ambiguity for symmetric objects. To address this, we propose SymCode, a symmetry-aware surface encoding that encodes the object surface vertices based on one-to-many correspondences, eliminating the problem of one-to-one correspondence ambiguity. We also introduce SymNet, a fast end-to-end network that directly regresses the 6D pose parameters without solving a PnP problem. We demonstrate faster runtime and comparable accuracy achieved by our method on the T-LESS and IC-BIN benchmarks of mostly symmetric objects. Our source code will be released upon acceptance.