Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition.
Xuanyu YiJiajun DengQianru SunXian-Sheng HuaJoo-Hwee LimHanwang ZhangPublished in: CoRR (2023)
Keyphrases
- point cloud
- training samples
- training set
- structure from motion
- surface reconstruction
- object recognition
- point cloud data
- laser scanner
- point sets
- real world objects
- feature extraction
- data sets
- triangular mesh
- pose estimation
- image registration
- video sequences
- video data
- affine invariant
- three dimensional
- high dimensional
- feature space