EUVIMEDEUVIMED entdecken
Crossref

BulletTime4D: Towards High Spatio-Temporal Resolution Dynamic Scene Rendering via Spike-Guided Stereo Vision

Yiqian Chang, Haoran Xu, Qinghong Ye, Jianing Li, Xuan Wang, Wei Zhang, Peixi Peng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2743-2751

DOI: 10.1609/aaai.v40i4.37263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yiqian Chang und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High spatio‑temporal resolution novel‑view scene rendering is crucial for applications such as sports analysis and scientific experiments. However, existing Dynamic Scene Rendering (DSR) approaches typically rely on conventional RGB cameras with limited frame rates, making it difficult to achieve high spatio‑temporal resolution. In this paper, we present BulletTime4D, a high spatio‑temporal resolution DSR framework, which is the first trial to integrate a spike camera with binocular RGB cameras for dynamic scene reconstruction. Specifically, we first develop a hybrid camera prototype and build a real‑world dynamic scene reconstruction dataset. Then, BulletTime4D presents a multi‑timescale deformation representation by combining low‑frequency spatio‑temporal features with high‑frequency inter‑frame motion features. Finally, a rendering network is designed capable of projecting 4D Gaussians into the spike domain for spike rendering, and a cross‑domain supervision strategy is proposed to achieve high‑frame‑rate texture and color rendering. The results show that BulletTime4D outperforms state‑of‑the‑art methods on both simulated and real‑world datasets. In addition, BulletTime4D can synthesize 300 FPS novel‑view renderings using stereo RGB cameras at 30 FPS and a single spike camera.

Zitieren

APA

Chang, Y., Xu, H., Ye, Q., Li, J., Wang, X., Zhang, W., & Peng, P. (2026). BulletTime4D: Towards High Spatio-Temporal Resolution Dynamic Scene Rendering via Spike-Guided Stereo Vision. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2743-2751. https://doi.org/10.1609/aaai.v40i4.37263

Vancouver

Chang Y, Xu H, Ye Q, Li J, Wang X, Zhang W, et al. BulletTime4D: Towards High Spatio-Temporal Resolution Dynamic Scene Rendering via Spike-Guided Stereo Vision. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2743-2751. doi:10.1609/aaai.v40i4.37263

BibTeX
@article{Chang2026,
  author = {Chang, Yiqian and Xu, Haoran and Ye, Qinghong and Li, Jianing and Wang, Xuan and Zhang, Wei and Peng, Peixi},
  title = {BulletTime4D: Towards High Spatio-Temporal Resolution Dynamic Scene Rendering via Spike-Guided Stereo Vision},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2743--2751},
  doi = {10.1609/aaai.v40i4.37263}
}
Kostenlos starten →