DiffNR：面向稀疏視角三維斷層重建的擴散增強神經表徵優化

摘要

神經表徵（如神經場與3D高斯模型）能有效建模電腦斷層掃描（CT）中的體積數據，但在稀疏投影設定下會產生嚴重偽影。為解決此問題，我們提出DiffNR——一種透過擴散先驗增強神經表徵優化的新框架。其核心組件SliceFixer是專為修正退化切片偽影設計的單步擴散模型。我們在網絡中整合了專用條件層，並開發了定制化的數據策展策略以支援模型微調。在重建過程中，SliceFixer會週期性生成偽參考體積，透過輔助3D感知監督來修復約束不足的區域。相較於將CT求解器嵌入耗時的迭代去噪過程的既有方法，我們的「修復-增強」策略避免了頻繁查詢擴散模型，從而實現更優的運行時效能。大量實驗表明，DiffNR平均提升PSNR達3.99 dB，具備良好的跨領域泛化能力，並能保持高效優化特性。

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.

DiffNR：面向稀疏視角三維斷層重建的擴散增強神經表徵優化

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

摘要

Support