Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

The dataset used in the paper is a multi-view image dataset, where each view is a 2D image of a 3D scene. The dataset is used to evaluate the performance of the Lift3D method, which is a framework for transforming 2D vision models to 3D predictions.

Data and Resources

Cite this as

Mukund Varma, Peihao Wang, Zhiwen Fan, Zhangyang Wang, Hao Su, Ravi Ramamoorthi (2024). Dataset: Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D. https://doi.org/10.57702/5kj8o1yg

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Mukund Varma
More Authors
Peihao Wang
Zhiwen Fan
Zhangyang Wang
Hao Su
Ravi Ramamoorthi