DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929281943207936 |
|---|---|
| author | Sun, Huiqiang Li, Xingyi Shen, Liao Ye, Xinyi Xian, Ke Cao, Zhiguo |
| author_facet | Sun, Huiqiang Li, Xingyi Shen, Liao Ye, Xinyi Xian, Ke Cao, Zhiguo |
| contents | Recent advancements in dynamic neural radiance field methods have yielded remarkable outcomes. However, these approaches rely on the assumption of sharp input images. When faced with motion blur, existing dynamic NeRF methods often struggle to generate high-quality novel views. In this paper, we propose DyBluRF, a dynamic radiance field approach that synthesizes sharp novel views from a monocular video affected by motion blur. To account for motion blur in input images, we simultaneously capture the camera trajectory and object Discrete Cosine Transform (DCT) trajectories within the scene. Additionally, we employ a global cross-time rendering approach to ensure consistent temporal coherence across the entire scene. We curate a dataset comprising diverse dynamic scenes that are specifically tailored for our task. Experimental results on our dataset demonstrate that our method outperforms existing approaches in generating sharp novel views from motion-blurred inputs while maintaining spatial-temporal consistency of the scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10103 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video Sun, Huiqiang Li, Xingyi Shen, Liao Ye, Xinyi Xian, Ke Cao, Zhiguo Computer Vision and Pattern Recognition Recent advancements in dynamic neural radiance field methods have yielded remarkable outcomes. However, these approaches rely on the assumption of sharp input images. When faced with motion blur, existing dynamic NeRF methods often struggle to generate high-quality novel views. In this paper, we propose DyBluRF, a dynamic radiance field approach that synthesizes sharp novel views from a monocular video affected by motion blur. To account for motion blur in input images, we simultaneously capture the camera trajectory and object Discrete Cosine Transform (DCT) trajectories within the scene. Additionally, we employ a global cross-time rendering approach to ensure consistent temporal coherence across the entire scene. We curate a dataset comprising diverse dynamic scenes that are specifically tailored for our task. Experimental results on our dataset demonstrate that our method outperforms existing approaches in generating sharp novel views from motion-blurred inputs while maintaining spatial-temporal consistency of the scene. |
| title | DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.10103 |