Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910361575227392 |
|---|---|
| author | Cao, Junyi Li, Zhichao Wang, Naiyan Ma, Chao |
| author_facet | Cao, Junyi Li, Zhichao Wang, Naiyan Ma, Chao |
| contents | Recent studies have highlighted the promising application of NeRF in autonomous driving contexts. However, the complexity of outdoor environments, combined with the restricted viewpoints in driving scenarios, complicates the task of precisely reconstructing scene geometry. Such challenges often lead to diminished quality in reconstructions and extended durations for both training and rendering. To tackle these challenges, we present Lightning NeRF. It uses an efficient hybrid scene representation that effectively utilizes the geometry prior from LiDAR in autonomous driving scenarios. Lightning NeRF significantly improves the novel view synthesis performance of NeRF and reduces computational overheads. Through evaluations on real-world datasets, such as KITTI-360, Argoverse2, and our private dataset, we demonstrate that our approach not only exceeds the current state-of-the-art in novel view synthesis quality but also achieves a five-fold increase in training speed and a ten-fold improvement in rendering speed. Codes are available at https://github.com/VISION-SJTU/Lightning-NeRF . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05907 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving Cao, Junyi Li, Zhichao Wang, Naiyan Ma, Chao Computer Vision and Pattern Recognition Robotics Recent studies have highlighted the promising application of NeRF in autonomous driving contexts. However, the complexity of outdoor environments, combined with the restricted viewpoints in driving scenarios, complicates the task of precisely reconstructing scene geometry. Such challenges often lead to diminished quality in reconstructions and extended durations for both training and rendering. To tackle these challenges, we present Lightning NeRF. It uses an efficient hybrid scene representation that effectively utilizes the geometry prior from LiDAR in autonomous driving scenarios. Lightning NeRF significantly improves the novel view synthesis performance of NeRF and reduces computational overheads. Through evaluations on real-world datasets, such as KITTI-360, Argoverse2, and our private dataset, we demonstrate that our approach not only exceeds the current state-of-the-art in novel view synthesis quality but also achieves a five-fold increase in training speed and a ten-fold improvement in rendering speed. Codes are available at https://github.com/VISION-SJTU/Lightning-NeRF . |
| title | Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2403.05907 |