Pose Anything: A Graph-Based Approach for Category-Agnostic Pose Estimation

29 Nov 2023  ·  Or Hirschorn, Shai Avidan ·

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 single model, requiring minimal support images with annotated keypoints. This approach not only enables object pose generation based on arbitrary keypoint definitions but also significantly reduces the associated costs, paving the way for versatile and adaptable pose estimation applications. We present a novel approach to CAPE that leverages the inherent geometrical relations between keypoints through a newly designed Graph Transformer Decoder. By capturing and incorporating this crucial structural information, our method enhances the accuracy of keypoint localization, marking a significant departure from conventional CAPE techniques that treat keypoints as isolated entities. We validate our approach on the MP-100 benchmark, a comprehensive dataset comprising over 20,000 images spanning more than 100 categories. Our method outperforms the prior state-of-the-art by substantial margins, achieving remarkable improvements of 2.16% and 1.82% under 1-shot and 5-shot settings, respectively. Furthermore, our method's end-to-end training demonstrates both scalability and efficiency compared to previous CAPE approaches.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
2D Pose Estimation MP-100 PoseAnything-S Mean PCK@0.2 - 1shot 90.43 # 1
Mean PCK@0.2 - 5shot 93.00 # 1
2D Pose Estimation MP-100 PoseAnything-T Mean PCK@0.2 - 1shot 87.47 # 2
Mean PCK@0.2 - 5shot 91.12 # 2