SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
This work addresses the challenge of robust and coherent keypoint estimation for 3D object understanding in practical scenarios, representing an incremental advance over existing unsupervised approaches.
The paper tackles the problem of estimating 3D keypoints from noisy, down-sampled, and rotated point cloud data without annotations, achieving improved coverage (+9.41%) and semantic consistency (+4.66%) compared to state-of-the-art unsupervised methods.
This paper proposes a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated. Our proposed model adheres to the following principles: i) keypoints inference is fully unsupervised (no annotation given), ii) keypoints position error should be low and resilient to PCD perturbations (robustness), iii) keypoints should not change their indexes for the intra-class objects (semantic coherence), iv) keypoints should be close to or proximal to PCD surface (compactness). We achieve these desiderata by proposing a new self-supervised training strategy for keypoints estimation that does not assume any a priori knowledge of the object class, and a model architecture with coupled auxiliary losses that promotes the desired keypoints properties. We compare the keypoints estimated by the proposed approach with those of the state-of-the-art unsupervised approaches. The experiments show that our approach outperforms by estimating keypoints with improved coverage (+9.41%) while being semantically consistent (+4.66%) that best characterizes the object's 3D shape for downstream tasks. Code and data are available at: https://github.com/IITPAVIS/SC3K