Self-supervised learning of rotation-invariant 3D point set features using transformer and its self-distillation.
Takahiko FuruyaZhoujie ChenRyutarou OhbuchiZhenzhong KuangPublished in: Comput. Vis. Image Underst. (2024)
Keyphrases
- rotation invariant
- point sets
- feature vectors
- rotation invariance
- learning algorithm
- feature space
- dominant orientation
- image features
- steerable filters
- supervised learning
- gabor filters
- texture analysis
- feature set
- affine transformation
- point correspondences
- image matching
- co occurrence
- object detection
- three dimensional
- feature selection
- computer vision