A Graph-Based Approach for Category-Agnostic Pose Estimation

TL;DR

This paper introduces a graph-based, category-agnostic pose estimation method that leverages keypoint relationships to improve accuracy across diverse object categories with minimal training data.

Contribution

It presents a novel graph-based approach for category-agnostic pose estimation, outperforming existing methods on the MP-100 benchmark with minimal support images.

Findings

Achieves a 0.98% performance boost in 1-shot setting

Sets new state-of-the-art results for CAPE

Validates approach on a large, diverse dataset

Abstract

Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories. This restriction becomes particularly challenging when dealing with novel objects due to the lack of relevant training data. To address this limitation, category-agnostic pose estimation (CAPE) was introduced. CAPE aims to enable keypoint localization for arbitrary object categories using a few-shot single model, requiring minimal support images with annotated keypoints. We present a significant departure from conventional CAPE techniques, which treat keypoints as isolated entities, by treating the input pose data as a graph. We leverage the inherent geometrical relations between keypoints through a graph-based network to break symmetry, preserve structure, and better handle occlusions. We validate our approach on the MP-100 benchmark, a comprehensive dataset comprising over 20,000 images spanning over 100 categories. Our solution boosts performance by 0.98% under a 1-shot setting, achieving a new state-of-the-art for CAPE. Additionally, we enhance the dataset with skeleton annotations. Our code and data are publicly available.