0

FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

FeatureNeRF leverages neural rendering to map 2D features to 3D semantic volumes, enhancing NeRF models for tasks like semantic keypoint transfer and object part segmentation.

Year
2023
Venue
ICCV 2023 1
Authors
3
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2303.12786ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Recent works on generalizable NeRFs have shown promising results on novel view synthesis from single or few images. However, such models have rarely been applied on other downstream tasks beyond synthesis such as semantic understanding and parsing. In this paper, we propose a novel framework named FeatureNeRF to learn generalizable NeRFs by distilling pre-trained vision foundation models (e.g., DINO, Latent Diffusion). FeatureNeRF leverages 2D pre-trained foundation models to 3D space via neural rendering, and then extract deep features for 3D query points from NeRF MLPs. Consequently, it allows to map 2D images to continuous 3D semantic feature volumes, which can be used for various downstream tasks. We evaluate FeatureNeRF on tasks of 2D/3D semantic keypoint transfer and 2D/3D object part segmentation. Our extensive experiments demonstrate the effectiveness of FeatureNeRF as a generalizable 3D semantic feature extractor. Our project page is available at https://jianglongye.com/featurenerf/ .

Authors

3