Skip to content

DylanOrange/geal

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

Dongyue Lu    Lingdong Kong    Tianxin Huang    Gim Hee Lee   
National University of Singapore   

About 🛠️

GEAL is a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging pre-trained 2D models. We employ a dual-branch architecture with Gaussian splatting to map 3D point clouds to 2D representations, enabling realistic renderings. Granularity-adaptive fusion and 2D-3D consistency alignment modules further strengthen cross-modal alignment and knowledge transfer, allowing the 3D branch to benefit from the rich semantics and generalization capacity of 2D models.

GEAL Performance GIF

Updates 📰

  • [2024.12] - We have released our PIAD-C and LASO-C datasets on Hugging Face! 🎉📂

Getting Started 🚀

To be updated.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published