TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction

TL;DR

TG-Field introduces a geometry-aware Gaussian deformation framework for improved static and dynamic CT reconstruction, effectively handling sparse views and motion artifacts with novel feature aggregation and motion modeling techniques.

Contribution

It presents a novel geometry-aware Gaussian deformation framework with multi-resolution encoding and motion modeling for enhanced CT reconstruction.

Findings

Outperforms existing methods on synthetic and real datasets.

Achieves state-of-the-art accuracy under sparse-view conditions.

Effectively models respiratory motion for dynamic reconstruction.

Abstract

3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view projections and dynamic motions. To address these challenges, we propose Tomographic Geometry Field (TG-Field), a geometry-aware Gaussian deformation framework tailored for both static and dynamic CT reconstruction. A multi-resolution hash encoder is employed to capture local spatial priors, regularizing primitive parameters under ultra-sparse settings. We further extend the framework to dynamic reconstruction by introducing time-conditioned representations and a spatiotemporal attention block to adaptively aggregate features, thereby resolving spatiotemporal ambiguities and enforcing temporal coherence. In addition, a motion-flow network models fine-grained respiratory motion to track local anatomical deformations. Extensive experiments on synthetic and real-world datasets demonstrate that TG-Field consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy under highly sparse-view conditions.