HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation

3D point cloud segmentation has received significant interest for its growing applications. However, the generalization ability of models suffers in dynamic scenarios due to the distribution shift between test and training data.

Data and Resources

Cite this as

Tianpei Zou, Sanqing Qu, Zhijun Li, Alois Knoll, Lianghua He, Guang Chen, Changjun Jiang (2024). Dataset: HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation. https://doi.org/10.57702/irlzamx3

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2407.12387
Author Tianpei Zou
More Authors
Sanqing Qu
Zhijun Li
Alois Knoll
Lianghua He
Guang Chen
Changjun Jiang
Homepage https://github.com/tpzou/HGL