SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dai, Gaole, Wang, Zhenyu, Xu, Qinwen, Lu, Ming, Chen, Wen, Shi, Boxin, Zhang, Shanghang, Huang, Tiejun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913311961907200
author Dai, Gaole
Wang, Zhenyu
Xu, Qinwen
Lu, Ming
Chen, Wen
Shi, Boxin
Zhang, Shanghang
Huang, Tiejun
author_facet Dai, Gaole
Wang, Zhenyu
Xu, Qinwen
Lu, Ming
Chen, Wen
Shi, Boxin
Zhang, Shanghang
Huang, Tiejun
contents One of the most critical factors in achieving sharp Novel View Synthesis (NVS) using neural field methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) is the quality of the training images. However, Conventional RGB cameras are susceptible to motion blur. In contrast, neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information, which can provide a sharp representation of the scene as additional training data. Recent methods have explored the integration of event cameras to improve the quality of NVS. The event-RGB approaches have some limitations, such as high training costs and the inability to work effectively in the background. Instead, our study introduces a new method that uses the spike camera to overcome these limitations. By considering texture reconstruction from spike streams as ground truth, we design the Texture from Spike (TfS) loss. Since the spike camera relies on temporal integration instead of temporal differentiation used by event cameras, our proposed TfS loss maintains manageable training costs. It handles foreground objects with backgrounds simultaneously. We also provide a real-world dataset captured with our spike-RGB camera system to facilitate future research endeavors. We conduct extensive experiments using synthetic and real-world datasets to demonstrate that our design can enhance novel view synthesis across NeRF and 3DGS. The code and dataset will be made available for public access.
format Preprint
id arxiv_https___arxiv_org_abs_2404_06710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera
Dai, Gaole
Wang, Zhenyu
Xu, Qinwen
Lu, Ming
Chen, Wen
Shi, Boxin
Zhang, Shanghang
Huang, Tiejun
Computer Vision and Pattern Recognition
Artificial Intelligence
One of the most critical factors in achieving sharp Novel View Synthesis (NVS) using neural field methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) is the quality of the training images. However, Conventional RGB cameras are susceptible to motion blur. In contrast, neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information, which can provide a sharp representation of the scene as additional training data. Recent methods have explored the integration of event cameras to improve the quality of NVS. The event-RGB approaches have some limitations, such as high training costs and the inability to work effectively in the background. Instead, our study introduces a new method that uses the spike camera to overcome these limitations. By considering texture reconstruction from spike streams as ground truth, we design the Texture from Spike (TfS) loss. Since the spike camera relies on temporal integration instead of temporal differentiation used by event cameras, our proposed TfS loss maintains manageable training costs. It handles foreground objects with backgrounds simultaneously. We also provide a real-world dataset captured with our spike-RGB camera system to facilitate future research endeavors. We conduct extensive experiments using synthetic and real-world datasets to demonstrate that our design can enhance novel view synthesis across NeRF and 3DGS. The code and dataset will be made available for public access.
title SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.06710