Saved in:
Bibliographic Details
Main Authors: Sivakumar, Piraveen, Janson, Paul, Rajasegaran, Jathushan, Ambegoda, Thanuja
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.04803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916350788632576
author Sivakumar, Piraveen
Janson, Paul
Rajasegaran, Jathushan
Ambegoda, Thanuja
author_facet Sivakumar, Piraveen
Janson, Paul
Rajasegaran, Jathushan
Ambegoda, Thanuja
contents In this paper, we address the challenge of generating novel views of real-world objects with limited multi-view images through our proposed approach, FewShotNeRF. Our method utilizes meta-learning to acquire optimal initialization, facilitating rapid adaptation of a Neural Radiance Field (NeRF) to specific scenes. The focus of our meta-learning process is on capturing shared geometry and textures within a category, embedded in the weight initialization. This approach expedites the learning process of NeRFs and leverages recent advancements in positional encodings to reduce the time required for fitting a NeRF to a scene, thereby accelerating the inner loop optimization of meta-learning. Notably, our method enables meta-learning on a large number of 3D scenes to establish a robust 3D prior for various categories. Through extensive evaluations on the Common Objects in 3D open source dataset, we empirically demonstrate the efficacy and potential of meta-learning in generating high-quality novel views of objects.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation
Sivakumar, Piraveen
Janson, Paul
Rajasegaran, Jathushan
Ambegoda, Thanuja
Computer Vision and Pattern Recognition
In this paper, we address the challenge of generating novel views of real-world objects with limited multi-view images through our proposed approach, FewShotNeRF. Our method utilizes meta-learning to acquire optimal initialization, facilitating rapid adaptation of a Neural Radiance Field (NeRF) to specific scenes. The focus of our meta-learning process is on capturing shared geometry and textures within a category, embedded in the weight initialization. This approach expedites the learning process of NeRFs and leverages recent advancements in positional encodings to reduce the time required for fitting a NeRF to a scene, thereby accelerating the inner loop optimization of meta-learning. Notably, our method enables meta-learning on a large number of 3D scenes to establish a robust 3D prior for various categories. Through extensive evaluations on the Common Objects in 3D open source dataset, we empirically demonstrate the efficacy and potential of meta-learning in generating high-quality novel views of objects.
title FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.04803