UC-NeRF: Uncertainty-Aware Conditional Neural Radiance Fields From Endoscopic Sparse Views
IEEE Transactions on Medical Imaging · 2025
DOI: 10.1109/tmi.2024.3496558 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Jiaxin Guo und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Endoscopy, Neural Networks, Computer, Image Processing, Computer-Assisted, Imaging, Three-Dimensional. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Shenzhen Portion of Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone, Research Grants Council of Hong Kong, Hong Kong Centre for Logistics Robotics; in part by the Multi-Scale Medical Robotics Centre, InnoHK.
Abstract (Originalsprache)
Visualizing surgical scenes is crucial for revealing internal anatomical structures during minimally invasive procedures. Novel View Synthesis is a vital technique that offers geometry and appearance reconstruction, enhancing understanding, planning, and decision-making in surgical scenes. Despite the impressive achievements of Neural Radiance Field (NeRF), its direct application to surgical scenes produces unsatisfying results due to two challenges: endoscopic sparse views and significant photometric inconsistencies. In this paper, we propose uncertainty-aware conditional NeRF for novel view synthesis to tackle the severe shape-radiance ambiguity from sparse surgical views. The core of UC-NeRF is to incorporate the multi-view uncertainty estimation to condition the neural radiance field for modeling the severe photometric inconsistencies adaptively. Specifically, our UC-NeRF first builds a consistency learner in the form of multi-view stereo network, to establish the geometric correspondence from sparse views and generate uncertainty estimation and feature priors. In neural rendering, we design a base-adaptive NeRF network to exploit the uncertainty estimation for explicitly handling the photometric inconsistencies. Furthermore, an uncertainty-guided geometry distillation is employed to enhance geometry learning. Experiments on the SCARED and Hamlyn datasets demonstrate our superior performance in rendering appearance and geometry, consistently outperforming the current state-of-the-art approaches. Our code will be released at https://github.com/wrld/UC-NeRF.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Shenzhen Portion of Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone
- Research Grants Council of Hong Kong
- Hong Kong Centre for Logistics Robotics; in part by the Multi-Scale Medical Robotics Centre, InnoHK
- VC Fund of CUHK T Stone Robotics Institute
Zitieren
APA
Guo, J., Wang, J., Wei, R., Kang, D., Dou, Q., & Liu, Y. H. (2025). UC-NeRF: Uncertainty-Aware Conditional Neural Radiance Fields From Endoscopic Sparse Views. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2024.3496558
Vancouver
Guo J, Wang J, Wei R, Kang D, Dou Q, Liu YH. UC-NeRF: Uncertainty-Aware Conditional Neural Radiance Fields From Endoscopic Sparse Views. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2024.3496558
BibTeX
@article{Guo2025,
author = {Guo, Jiaxin and Wang, Jiangliu and Wei, Ruofeng and Kang, Di and Dou, Qi and Liu, Yun-Hui},
title = {UC-NeRF: Uncertainty-Aware Conditional Neural Radiance Fields From Endoscopic Sparse Views},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
doi = {10.1109/tmi.2024.3496558}
}
EUVIMED