HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kania, Adam, Kasymov, Artur, Kościukiewicz, Jakub, Górak, Artur, Mazur, Marcin, Zięba, Maciej, Spurek, Przemysław
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913476037836800
author Kania, Adam
Kasymov, Artur
Kościukiewicz, Jakub
Górak, Artur
Mazur, Marcin
Zięba, Maciej
Spurek, Przemysław
author_facet Kania, Adam
Kasymov, Artur
Kościukiewicz, Jakub
Górak, Artur
Mazur, Marcin
Zięba, Maciej
Spurek, Przemysław
contents The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated with training with conventional 3D representations, such as voxels or point clouds. Neural Radiance Fields (NeRFs), which provide the current benchmark in terms of quality for the generation of novel views of complex 3D scenes from a limited set of 2D images, represent a promising solution to this challenge. However, the training of these models requires the knowledge of the respective camera positions from which the images were viewed. In this paper, we overcome this limitation by introducing HyperNeRFGAN, a Generative Adversarial Network (GAN) architecture employing a hypernetwork paradigm to transform a Gaussian noise into the weights of a NeRF architecture that does not utilize viewing directions in its training phase. Consequently, as evidenced by the findings of our experimental study, the proposed model, despite its notable simplicity in comparison to existing state-of-the-art alternatives, demonstrates superior performance on a diverse range of image datasets where camera position estimation is challenging, particularly in the context of medical data.
format Preprint
id arxiv_https___arxiv_org_abs_2301_11631
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
Kania, Adam
Kasymov, Artur
Kościukiewicz, Jakub
Górak, Artur
Mazur, Marcin
Zięba, Maciej
Spurek, Przemysław
Computer Vision and Pattern Recognition
The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated with training with conventional 3D representations, such as voxels or point clouds. Neural Radiance Fields (NeRFs), which provide the current benchmark in terms of quality for the generation of novel views of complex 3D scenes from a limited set of 2D images, represent a promising solution to this challenge. However, the training of these models requires the knowledge of the respective camera positions from which the images were viewed. In this paper, we overcome this limitation by introducing HyperNeRFGAN, a Generative Adversarial Network (GAN) architecture employing a hypernetwork paradigm to transform a Gaussian noise into the weights of a NeRF architecture that does not utilize viewing directions in its training phase. Consequently, as evidenced by the findings of our experimental study, the proposed model, despite its notable simplicity in comparison to existing state-of-the-art alternatives, demonstrates superior performance on a diverse range of image datasets where camera position estimation is challenging, particularly in the context of medical data.
title HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2301.11631