Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

2026-08-05

AI Summary

This work addresses the severe streaking artifacts in splat-based sparse-view CT reconstruction caused by inaccurate pose estimates in real-world systems. It reveals that splat-based methods are inherently highly sensitive to geometric misalignment and, for the first time, integrates pose correction directly into a differentiable splatting reconstruction pipeline. By introducing a lightweight gradient-based optimization framework, the method jointly refines geometric parameters and the 3D Gaussian splat representation during reconstruction, effectively suppressing streaking artifacts. This approach substantially improves reconstruction fidelity under sparse-view conditions and can be readily incorporated into existing CT reconstruction workflows.

Abstract

X-ray computed tomography (CT) reconstructs volumetric representations of objects from projection images obtained by transmitting X-rays through a target. Recent splat-based tomography, which represents a volume as a continuous distribution of 3D Gaussians, has demonstrated both high reconstruction quality and fast convergence in cone-beam sparse-view CT. However, when deployed in real CT systems with limited and non-uniform view distributions, we observe distinctive streak and strip artifacts that are far more pronounced than in conventional reconstruction methods. Through detailed analysis, we show that these artifacts primarily originate from pose inaccuracies in the acquisition geometry rather than from view sparsity itself. We revisit pose sensitivity in the splatting formulation and derive a stable gradient-based framework that jointly refines geometric parameters during reconstruction. Our study not only identifies how pose perturbations propagate through the differentiable projection operator but also reveals why splat-based CT is particularly vulnerable to geometric misalignment. The resulting formulation remains lightweight and easily integrable into existing pipelines while substantially improving reconstruction fidelity under real-world sparse-view conditions.

Problem

• pose sensitivity
• sparse-view CT
• splat-based reconstruction
• geometric misalignment
• reconstruction artifacts

Innovation

• pose sensitivity
• splat-based CT
• sparse-view reconstruction
• geometric misalignment
• differentiable projection