Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation

TL;DR

This paper introduces a novel multi-reference-based approach for 6D object pose estimation that employs positional encoding and a robust refinement strategy, significantly improving accuracy on standard datasets.

Contribution

The paper proposes new strategies using positional encoding and a normalized multi-reference refinement to overcome limitations of existing pose estimation methods.

Findings

Outperforms existing methods on Linemod, Linemod-Occlusion, and YCB-Video datasets.

Uses high-frequency positional encoding for better geometric representation.

Employs adaptive normalization and occlusion augmentation to enhance model focus.

Abstract

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have some limitations that reduce their effectiveness. In this paper, we analyze these limitations and propose new strategies to overcome them. To tackle the issue of blurry geometric representation, we use positional encoding with high-frequency components for the object's 3D coordinates. To address the local minimum problem in refinement methods, we introduce a normalized image plane-based multi-reference refinement strategy that's independent of intrinsic matrix constraints. Lastly, we utilize adaptive instance normalization and a simple occlusion augmentation method to help our model concentrate on the target object. Our experiments on Linemod, Linemod-Occlusion, and YCB-Video datasets demonstrate that our approach outperforms existing methods. We will soon release the code.