EUVIMEDEUVIMED entdecken
Crossref

DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction

Shiyan Su, Ruyi Zha, Danli Shi, Hongdong Li, Xuelian Cheng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (11) · 9144-9152

DOI: 10.1609/aaai.v40i11.37871 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shiyan Su und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel framework that enhances NR optimization with diffusion priors. At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices. We integrate specialized conditioning layers into the network and develop tailored data curation strategies to support model finetuning. During reconstruction, SliceFixer periodically generates pseudo-reference volumes, providing auxiliary 3D perceptual supervision to fix underconstrained regions. Compared to prior methods that embed CT solvers into time-consuming iterative denoising, our repair-and-augment strategy avoids frequent diffusion model queries, leading to better runtime performance. Extensive experiments show that DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.

Zitieren

APA

Su, S., Zha, R., Shi, D., Li, H., & Cheng, X. (2026). DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(11), 9144-9152. https://doi.org/10.1609/aaai.v40i11.37871

Vancouver

Su S, Zha R, Shi D, Li H, Cheng X. DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(11):9144-9152. doi:10.1609/aaai.v40i11.37871

BibTeX
@article{Su2026,
  author = {Su, Shiyan and Zha, Ruyi and Shi, Danli and Li, Hongdong and Cheng, Xuelian},
  title = {DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {11},
  pages = {9144--9152},
  doi = {10.1609/aaai.v40i11.37871}
}
Kostenlos starten →