VDNeRF: Vision‐Only Dynamic Neural Radiance Field for Urban Scenes
CAAI Transactions on Intelligence Technology · 2026-10 · 11 (5) · 1585-1599
DOI: 10.1049/cit2.70086 ↗Kurz gefasst
Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 07.08.2026. Verfasst von Zhengyu Zou und 7 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Neural radiance fields (NeRFs) implicitly model continuous three‐dimensional scenes using a set of images with known camera poses, enabling the rendering of photorealistic novel views. However, existing NeRF‐based methods encounter challenges in applications such as autonomous driving and robotic perception, primarily due to the difficulty of capturing accurate camera poses and limitations in handling large‐scale dynamic environments. To address these issues, we propose vision‐only dynamic NeRF (VDNeRF), a method that accurately recovers camera trajectories and learns spatiotemporal representations for dynamic urban scenes without requiring additional camera pose information or expensive sensor data. VDNeRF employs two separate NeRF models to jointly reconstruct the scene. The static NeRF model optimises camera poses and static background, whereas the dynamic NeRF model incorporates the 3D scene flow to ensure accurate and consistent reconstruction of dynamic objects. To address the ambiguity between camera motion and independent object motion, we design an effective and powerful training framework to achieve robust camera pose estimation and self‐supervised decomposition of static and dynamic elements in a scene. Extensive evaluations on mainstream urban driving datasets demonstrate that VDNeRF surpasses state‐of‐the‐art NeRF‐based pose‐free methods in both camera pose estimation and dynamic novel view synthesis.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zou, Z., Li, J., Li, H., Hou, X., Hu, J., Chen, J., Cheng, L., & Zhang, D. (2026). VDNeRF: Vision‐Only Dynamic Neural Radiance Field for Urban Scenes. CAAI Transactions on Intelligence Technology, 11(5), 1585-1599. https://doi.org/10.1049/cit2.70086
Vancouver
Zou Z, Li J, Li H, Hou X, Hu J, Chen J, et al. VDNeRF: Vision‐Only Dynamic Neural Radiance Field for Urban Scenes. CAAI Transactions on Intelligence Technology. 2026;11(5):1585-1599. doi:10.1049/cit2.70086
BibTeX
@article{Zou2026,
author = {Zou, Zhengyu and Li, Jingfeng and Li, Hao and Hou, Xiaolei and Hu, Jinwen and Chen, Jingkun and Cheng, Lechao and Zhang, Dingwen},
title = {VDNeRF: Vision‐Only Dynamic Neural Radiance Field for Urban Scenes},
journal = {CAAI Transactions on Intelligence Technology},
year = {2026},
volume = {11},
number = {5},
pages = {1585--1599},
doi = {10.1049/cit2.70086}
}
EUVIMED