ρ-NeRF: Leveraging Attenuation Priors in Neural Radiance Field for 3D Computed Tomography Reconstruction

Abstract

This paper introduces \(\rho\)-NeRF, a self-supervised approach that sets a new standard in novel view synthesis (NVS) and computed tomography (CT) reconstruction by modeling a continuous volumetric radiance field enriched with physics-based attenuation priors. The \(\rho\)-NeRF represents a three-dimensional (3D) volume through a fully-connected neural network that takes a single continuous four-dimensional (4D) coordinate—spatial location \((x,y,z)\) and an initialized attenuation value \((\rho)\)—and outputs the attenuation coefficient at that position. By querying these 4D coordinates along X-ray paths, the classic forward projection technique is applied to integrate attenuation data across the 3D space. By matching and refining pre-initialized attenuation values derived from traditional reconstruction algorithms like Feldkamp-Davis-Kress algorithm (FDK) or conjugate gradient least squares (CGLS), the enriched schema delivers superior fidelity in both projection synthesis and image reconstruction, with negligible extra computational overhead. The paper details the optimization of \(\rho\)-NeRF for accurate NVS and high-quality CT reconstruction from a limited number of projections, setting a new standard for sparse-view CT applications.