Search papers, labs, and topics across Lattice.
The paper introduces Tomographic Geometry Field (TG-Field), a novel 3D Gaussian Splatting (3DGS) framework designed to improve CT reconstruction, especially under sparse-view projections and dynamic motions. TG-Field incorporates a multi-resolution hash encoder to inject spatial priors for regularization and uses time-conditioned representations with a spatiotemporal attention block to handle dynamic reconstruction. Experiments on both synthetic and real-world CT datasets demonstrate that TG-Field achieves state-of-the-art reconstruction accuracy compared to existing methods in sparse-view scenarios.
Achieve state-of-the-art CT reconstruction accuracy under highly sparse-view conditions by deforming 3D Gaussians with a geometry-aware field.
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.
