MaskLRF: Self-Supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-Invariant 3D Point Set Analysis
Following the successes in the fields of vision and language, self-supervised pretraining via masked autoencoding of 3D point set data, or Masked Point Modeling (MPM), has achieved state-of-the-art accuracy in various downstream tasks. However, current MPM methods lack a property essential for 3D po...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| التنسيق: | Artigo |
| اللغة: | Inglês |
| منشور في: |
IEEE
2024-01-01
|
| سلاسل: | IEEE Access |
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://ieeexplore.ieee.org/document/10536090/ |
| الوسوم: |
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|