TriNeRFLet: A Wavelet Based Triplane NeRF Representation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Khatib, Rajaei, Giryes, Raja
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909260412092416
author Khatib, Rajaei
Giryes, Raja
author_facet Khatib, Rajaei
Giryes, Raja
contents In recent years, the neural radiance field (NeRF) model has gained popularity due to its ability to recover complex 3D scenes. Following its success, many approaches proposed different NeRF representations in order to further improve both runtime and performance. One such example is Triplane, in which NeRF is represented using three 2D feature planes. This enables easily using existing 2D neural networks in this framework, e.g., to generate the three planes. Despite its advantage, the triplane representation lagged behind in its 3D recovery quality compared to NeRF solutions. In this work, we propose TriNeRFLet, a 2D wavelet-based multiscale triplane representation for NeRF, which closes the 3D recovery performance gap and is competitive with current state-of-the-art methods. Building upon the triplane framework, we also propose a novel super-resolution (SR) technique that combines a diffusion model with TriNeRFLet for improving NeRF resolution.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06191
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TriNeRFLet: A Wavelet Based Triplane NeRF Representation
Khatib, Rajaei
Giryes, Raja
Computer Vision and Pattern Recognition
In recent years, the neural radiance field (NeRF) model has gained popularity due to its ability to recover complex 3D scenes. Following its success, many approaches proposed different NeRF representations in order to further improve both runtime and performance. One such example is Triplane, in which NeRF is represented using three 2D feature planes. This enables easily using existing 2D neural networks in this framework, e.g., to generate the three planes. Despite its advantage, the triplane representation lagged behind in its 3D recovery quality compared to NeRF solutions. In this work, we propose TriNeRFLet, a 2D wavelet-based multiscale triplane representation for NeRF, which closes the 3D recovery performance gap and is competitive with current state-of-the-art methods. Building upon the triplane framework, we also propose a novel super-resolution (SR) technique that combines a diffusion model with TriNeRFLet for improving NeRF resolution.
title TriNeRFLet: A Wavelet Based Triplane NeRF Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.06191