Few-shot 3D Point Cloud Semantic Segmentation
3 papers with code • 1 benchmarks • 1 datasets
S3DIS
Most implemented papers
Few-shot 3D Point Cloud Semantic Segmentation
These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training.
Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network
While a few-shot learning method was proposed recently to address these two problems, it suffers from high computational complexity caused by graph construction and inability to learn fine-grained relationships among points due to the use of pooling operations.
Rethinking Few-shot 3D Point Cloud Semantic Segmentation
The former arises from non-uniform point sampling, allowing models to distinguish the density disparities between foreground and background for easier segmentation.
