DS-MAE: Dual-Siamese masked autoencoders for point cloud analysis
Masked autoencoders (MAEs) have emerged as a powerful self-supervised approach for point cloud analysis. Nevertheless, existing methods often separately focus on global structures or multi-scale features, ignoring their complementary potential. In this paper, we propose a novel dual-Siamese masked a...
I tiakina i:
| Ngā kaituhi matua: | , , , , , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
Tsinghua University Press
2025-08-01
|
| Rangatū: | Computational Visual Media |
| Ngā marau: | |
| Urunga tuihono: | https://www.sciopen.com/article/10.26599/CVM.2025.9450487 |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|