用扩散模型修复稀疏视角下的3D断层重建伪影，提升质量且更快。
DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
- 引入单步扩散模型SliceFixer，实时修正低视角重建中的切片伪影。
- 平均提升PSNR 3.99 dB，且在不同数据域间泛化能力强。
- 无需反复调用扩散模型，优化效率高，适合实际医学成像应用。
神经表示（NRs）如神经场和3D高斯，在计算机断层扫描（CT）中能有效建模体数据，但在稀疏视角条件下会产生严重伪影。为此，我们提出DiffNR，一种通过扩散先验增强NR优化的新框架。核心是SliceFixer——一个单步扩散模型，用于纠正退化切片中的伪影。我们在网络中集成特定的条件层，并开发定制化的数据整理策略以支持模型微调。重建过程中，SliceFixer周期性生成伪参考体积，为欠约束区域提供辅助3D感知监督。相比将CT求解器嵌入耗时的迭代去噪的方法，我们的修复与增强策略避免了频繁调用扩散模型，从而实现更优的运行效率。大量实验表明，DiffNR平均提升PSNR 3.99 dB，跨领域泛化良好，且保持高效优化。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。