OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation
This addresses the problem of estimating poses for articulated objects in real-world scenarios with reduced annotation costs, though it is incremental as it builds on existing self-supervised and supervised approaches.
The paper tackles category-level articulated object pose estimation from single-frame point clouds by proposing a self-supervised method that aligns object-level and part-level poses, achieving results comparable to state-of-the-art supervised methods.
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.