OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation

2024-08-29

European Conference on Computer Vision

AI Summary

Existing category-level pose estimation methods for articulated objects with known categories but unknown geometries suffer from high annotation costs, reliance on multi-view inputs, or strong supervision. This paper proposes the first unsupervised, single-frame point cloud-based category-level pose estimation framework. It introduces a self-supervised paradigm that jointly optimizes canonical global pose and joint states through object-level and part-level co-alignment. Key technical components include a point-cloud autoencoder for canonical reconstruction, differentiable part segmentation, hierarchical pose disentanglement, and joint-aware geometric consistency constraints. Contributions are threefold: (1) the first object-part co-alignment mechanism for articulated pose estimation; (2) the first large-scale real-scene articulated object benchmark dataset; and (3) competitive performance against state-of-the-art supervised methods on multiple benchmarks, with strong generalization and robustness validated on the new dataset.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Object Detection & Categorization
• Machine Learning: Unsupervised & Self-Supervised Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Category-level articulated object pose estimation focuses on the pose estimation of unknown articulated objects within known categories. Despite its significance, this task remains challenging due to the varying shapes and poses of objects, expensive dataset annotation costs, and complex real-world environments. In this paper, we propose a novel self-supervised approach that leverages a single-frame point cloud to solve this task. Our model consistently generates reconstruction with a canonical pose and joint state for the entire input object, and it estimates object-level poses that reduce overall pose variance and part-level poses that align each part of the input with its corresponding part of the reconstruction. Experimental results demonstrate that our approach significantly outperforms previous self-supervised methods and is comparable to the state-of-the-art supervised methods. To assess the performance of our model in real-world scenarios, we also introduce a new real-world articulated object benchmark dataset.

Problem

• Estimates poses of unknown articulated objects in known categories
• Addresses shape and pose variations without expensive annotations
• Aligns object and part levels for accurate pose reconstruction

Innovation

• Self-supervised single-frame point cloud alignment method
• Object-level and part-level pose estimation for canonical reconstruction
• Real-world articulated object benchmark dataset introduction