EUVIMEDEUVIMED entdecken
Crossref

MS-NeRF: Multi-Space Neural Radiance Fields

Ze-Xin Yin, Peng-Yi Jiao, Jiaxiong Qiu, Ming-Ming Cheng, Bo Ren

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-05 · 47 (5) · 3766-3783

DOI: 10.1109/tpami.2025.3540074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-05. Verfasst von Ze-Xin Yin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Tianjin science and technology projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects, often resulting in blurry or distorted rendering. Instead of calculating a single radiance field, we propose a multi-space neural radiance field (MS-NeRF) that represents the scene using a group of feature fields in parallel sub-spaces, which leads to a better understanding of the neural network toward the existence of reflective and refractive objects. Our multi-space scheme works as an enhancement to existing NeRF methods, with only small computational overheads needed for training and inferring the extra-space outputs. We design different multi-space modules for representative MLP-based and grid-based NeRF methods, which improve Mip-NeRF 360 by 4.15 dB in PSNR with 0.5% extra parameters and further improve TensoRF by 2.71 dB with 0.046% extra parameters on reflective regions without degrading the rendering quality on other regions. We further construct a novel dataset consisting of 33 synthetic scenes and 7 real captured scenes with complex reflection and refraction, where we design complex camera paths to fully benchmark the robustness of NeRF-based methods. Extensive experiments show that our approach significantly outperforms the existing single-space NeRF methods for rendering high-quality scenes concerned with complex light paths through mirror-like objects.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Tianjin science and technology projects
  • Supercomputing Center of Nankai University

Zitieren

APA

Yin, Z. X., Jiao, P. Y., Qiu, J., Cheng, M. M., & Ren, B. (2025). MS-NeRF: Multi-Space Neural Radiance Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3766-3783. https://doi.org/10.1109/tpami.2025.3540074

Vancouver

Yin ZX, Jiao PY, Qiu J, Cheng MM, Ren B. MS-NeRF: Multi-Space Neural Radiance Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(5):3766-3783. doi:10.1109/tpami.2025.3540074

BibTeX
@article{Yin2025,
  author = {Yin, Ze-Xin and Jiao, Peng-Yi and Qiu, Jiaxiong and Cheng, Ming-Ming and Ren, Bo},
  title = {MS-NeRF: Multi-Space Neural Radiance Fields},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {5},
  pages = {3766--3783},
  doi = {10.1109/tpami.2025.3540074}
}
Kostenlos starten →