Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset
This work addresses the challenge of limited annotated data for pose estimation in robotics and computer vision, offering a solution for real-world applications, though it is incremental as it builds on existing semi-supervised techniques.
The paper tackles the problem of category-level 6D object pose estimation in unconstrained environments by introducing a semi-supervised learning approach and a new dataset called Wild6D. The result is that their method, RePoNet, outperforms state-of-the-art methods by a large margin on both previous datasets and the Wild6D test set, without using any 3D annotations on real data.
6D object pose estimation is one of the fundamental problems in computer vision and robotics research. While a lot of recent efforts have been made on generalizing pose estimation to novel object instances within the same category, namely category-level 6D pose estimation, it is still restricted in constrained environments given the limited number of annotated data. In this paper, we collect Wild6D, a new unlabeled RGBD object video dataset with diverse instances and backgrounds. We utilize this data to generalize category-level 6D object pose estimation in the wild with semi-supervised learning. We propose a new model, called Rendering for Pose estimation network RePoNet, that is jointly trained using the free ground-truths with the synthetic data, and a silhouette matching objective function on the real-world data. Without using any 3D annotations on real data, our method outperforms state-of-the-art methods on the previous dataset and our Wild6D test set (with manual annotations for evaluation) by a large margin. Project page with Wild6D data: https://oasisyang.github.io/semi-pose .