Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Min, Zhiyuan, Luo, Yawei, Yang, Wei, Wang, Yuesong, Yang, Yi
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909134476017664
author Min, Zhiyuan
Luo, Yawei
Yang, Wei
Wang, Yuesong
Yang, Yi
author_facet Min, Zhiyuan
Luo, Yawei
Yang, Wei
Wang, Yuesong
Yang, Yi
contents Generalizable NeRF can directly synthesize novel views across new scenes, eliminating the need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these approaches is the extraction of a generalizable 3D representation by aggregating source-view features. In this paper, we propose an Entangled View-Epipolar Information Aggregation method dubbed EVE-NeRF. Different from existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process. Our approach effectively mitigates the potential lack of inherent geometric and appearance constraint resulting from one-dimensional interactions, thus further boosting the 3D representation generalizablity. EVE-NeRF attains state-of-the-art performance across various evaluation scenarios. Extensive experiments demonstate that, compared to prevailing single-dimensional aggregation, the entangled network excels in the accuracy of 3D scene geometry and appearance reconstruction. Our code is publicly available at https://github.com/tatakai1/EVENeRF.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11845
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
Min, Zhiyuan
Luo, Yawei
Yang, Wei
Wang, Yuesong
Yang, Yi
Computer Vision and Pattern Recognition
Generalizable NeRF can directly synthesize novel views across new scenes, eliminating the need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these approaches is the extraction of a generalizable 3D representation by aggregating source-view features. In this paper, we propose an Entangled View-Epipolar Information Aggregation method dubbed EVE-NeRF. Different from existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process. Our approach effectively mitigates the potential lack of inherent geometric and appearance constraint resulting from one-dimensional interactions, thus further boosting the 3D representation generalizablity. EVE-NeRF attains state-of-the-art performance across various evaluation scenarios. Extensive experiments demonstate that, compared to prevailing single-dimensional aggregation, the entangled network excels in the accuracy of 3D scene geometry and appearance reconstruction. Our code is publicly available at https://github.com/tatakai1/EVENeRF.
title Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.11845