albumentationsRepository32/100 via “keypoint-aware spatial augmentation with skeleton consistency”
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless
Unique: Uses shared coordinate transformation matrices with bbox transforms, enabling consistent handling of multiple annotation types (images, bboxes, keypoints) in a single pipeline; supports optional skeleton validation via configurable joint connection graphs
vs others: More comprehensive than torchvision for keypoint augmentation because it handles multiple annotation types simultaneously; more flexible than custom pose augmentation code because it abstracts coordinate transformations