Back to Search Start Over

Probing the 3D Awareness of Visual Foundation Models

Authors :
Banani, Mohamed El
Raj, Amit
Maninis, Kevis-Kokitsi
Kar, Abhishek
Li, Yuanzhen
Rubinstein, Michael
Sun, Deqing
Guibas, Leonidas
Johnson, Justin
Jampani, Varun
Publication Year :
2024

Abstract

Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their intermediate representations are useful for other visual tasks such as detection and segmentation. Given that such models can classify, delineate, and localize objects in 2D, we ask whether they also represent their 3D structure? In this work, we analyze the 3D awareness of visual foundation models. We posit that 3D awareness implies that representations (1) encode the 3D structure of the scene and (2) consistently represent the surface across views. We conduct a series of experiments using task-specific probes and zero-shot inference procedures on frozen features. Our experiments reveal several limitations of the current models. Our code and analysis can be found at https://github.com/mbanani/probe3d.<br />Comment: Accepted to CVPR 2024. Project page: https://github.com/mbanani/probe3d

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2404.08636
Document Type :
Working Paper