Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation
Authors:
- Enze XieEXEnze Xie
- Matthias NießnerMNMatthias Nießner
- 31 October 2024
- book chapter
- Published by Springer Nature
- p. 354-370
Abstract
No abstract availableKeywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Objaverse: A Universe of Annotated 3D Objects2023
- All are Worth Words: A ViT Backbone for Diffusion Models2023
- Scaling Language-Image Pre-Training via Masking2023
- MaskGIT: Masked Generative Image Transformer2022
- Masked Autoencoders Are Scalable Vision Learners2022
- Diffusion Probabilistic Models for 3D Point Cloud Generation2021
- SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data2021
- Discrete Point Flow Networks for Efficient Point Cloud Generation2020
- Multiresolution Tree Networks for 3D Point Cloud Processing2018
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation2018