EUVIMEDEUVIMED entdecken
Crossref

Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis

Phong Nguyen-Ha, Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 2758-2769

DOI: 10.1109/tpami.2023.3335311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Phong Nguyen-Ha und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Research Council of Finland.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views using a set of nearby input views. However, the rendering speed is still slow due to the nature of uniformly-point sampling of neural radiance fields. Existing scene-specific methods can train and render novel views efficiently but can not generalize to unseen data. Our approach addresses the problems of fast and generalizing view synthesis by proposing two novel modules: a coarse radiance fields predictor and a convolutional-based neural renderer. This architecture infers consistent scene geometry based on the implicit neural fields and renders new views efficiently using a single GPU. We first train CG-NeRF on multiple 3D scenes of the DTU dataset, and the network can produce high-quality and accurate novel views on unseen real and synthetic data using only photometric losses. Moreover, our method can leverage a denser set of reference images of a single scene to produce accurate novel views without relying on additional explicit representations and still maintains the high-speed rendering of the pre-trained model. Experimental results show that CG-NeRF outperforms state-of-the-art generalizable neural rendering methods on various synthetic and real datasets.

Förderung

  • Research Council of Finland

Zitieren

APA

Nguyen-Ha, P., Huynh, L., Rahtu, E., Matas, J., & Heikkila, J. (2024). Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 2758-2769. https://doi.org/10.1109/tpami.2023.3335311

Vancouver

Nguyen-Ha P, Huynh L, Rahtu E, Matas J, Heikkila J. Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):2758-2769. doi:10.1109/tpami.2023.3335311

BibTeX
@article{NguyenHa2024,
  author = {Nguyen-Ha, Phong and Huynh, Lam and Rahtu, Esa and Matas, Jiri and Heikkila, Janne},
  title = {Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {5},
  pages = {2758--2769},
  doi = {10.1109/tpami.2023.3335311}
}
Kostenlos starten →