NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Weining, Zhu, Zihan, Sun, Boyang, Chen, Jiaqi, Pollefeys, Marc, Peng, Songyou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913373034119168
author Ren, Weining
Zhu, Zihan
Sun, Boyang
Chen, Jiaqi
Pollefeys, Marc
Peng, Songyou
author_facet Ren, Weining
Zhu, Zihan
Sun, Boyang
Chen, Jiaqi
Pollefeys, Marc
Peng, Songyou
contents Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in render quality, especially under high occlusion scenarios. In this paper, we introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes from only casually captured image sequences. Delving into uncertainty, our method not only efficiently eliminates distractors, even when they are predominant in captures, but also achieves a notably faster convergence speed. Through comprehensive experiments on various scenes, our method demonstrates a significant improvement over state-of-the-art techniques. This advancement opens new avenues for NeRF in diverse and dynamic real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
Ren, Weining
Zhu, Zihan
Sun, Boyang
Chen, Jiaqi
Pollefeys, Marc
Peng, Songyou
Computer Vision and Pattern Recognition
Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in render quality, especially under high occlusion scenarios. In this paper, we introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes from only casually captured image sequences. Delving into uncertainty, our method not only efficiently eliminates distractors, even when they are predominant in captures, but also achieves a notably faster convergence speed. Through comprehensive experiments on various scenes, our method demonstrates a significant improvement over state-of-the-art techniques. This advancement opens new avenues for NeRF in diverse and dynamic real-world applications.
title NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18715