FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qian, Rui, Zhang, Chenyangguang, Di, Yan, Zhai, Guangyao, Zhang, Ruida, Guo, Jiayu, Busam, Benjamin, Pu, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929761551384576
author Qian, Rui
Zhang, Chenyangguang
Di, Yan
Zhai, Guangyao
Zhang, Ruida
Guo, Jiayu
Busam, Benjamin
Pu, Jian
author_facet Qian, Rui
Zhang, Chenyangguang
Di, Yan
Zhai, Guangyao
Zhang, Ruida
Guo, Jiayu
Busam, Benjamin
Pu, Jian
contents Neural Radiance Fields (NeRF) have exhibited highly effective performance for photorealistic novel view synthesis recently. However, the key limitation it meets is the reliance on a hand-crafted frequency annealing strategy to recover 3D scenes with imperfect camera poses. The strategy exploits a temporal low-pass filter to guarantee convergence while decelerating the joint optimization of implicit scene reconstruction and camera registration. In this work, we introduce the Frequency Adapted Bundle Adjusting Radiance Field (FA-BARF), substituting the temporal low-pass filter for a frequency-adapted spatial low-pass filter to address the decelerating problem. We establish a theoretical framework to interpret the relationship between position encoding of NeRF and camera registration and show that our frequency-adapted filter can mitigate frequency fluctuation caused by the temporal filter. Furthermore, we show that applying a spatial low-pass filter in NeRF can optimize camera poses productively through radial uncertainty overlaps among various views. Extensive experiments show that FA-BARF can accelerate the joint optimization process under little perturbations in object-centric scenes and recover real-world scenes with unknown camera poses. This implies wider possibilities for NeRF applied in dense 3D mapping and reconstruction under real-time requirements. The code will be released upon paper acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields
Qian, Rui
Zhang, Chenyangguang
Di, Yan
Zhai, Guangyao
Zhang, Ruida
Guo, Jiayu
Busam, Benjamin
Pu, Jian
Computer Vision and Pattern Recognition
Neural Radiance Fields (NeRF) have exhibited highly effective performance for photorealistic novel view synthesis recently. However, the key limitation it meets is the reliance on a hand-crafted frequency annealing strategy to recover 3D scenes with imperfect camera poses. The strategy exploits a temporal low-pass filter to guarantee convergence while decelerating the joint optimization of implicit scene reconstruction and camera registration. In this work, we introduce the Frequency Adapted Bundle Adjusting Radiance Field (FA-BARF), substituting the temporal low-pass filter for a frequency-adapted spatial low-pass filter to address the decelerating problem. We establish a theoretical framework to interpret the relationship between position encoding of NeRF and camera registration and show that our frequency-adapted filter can mitigate frequency fluctuation caused by the temporal filter. Furthermore, we show that applying a spatial low-pass filter in NeRF can optimize camera poses productively through radial uncertainty overlaps among various views. Extensive experiments show that FA-BARF can accelerate the joint optimization process under little perturbations in object-centric scenes and recover real-world scenes with unknown camera poses. This implies wider possibilities for NeRF applied in dense 3D mapping and reconstruction under real-time requirements. The code will be released upon paper acceptance.
title FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12086