Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction

TL;DR

This paper introduces a novel active view selection method for X-ray CT reconstruction that uses an ensemble of Gaussian models to identify uncertain views, improving image quality and reducing artifacts.

Contribution

The paper proposes Perturbed Gaussian Ensemble, a new framework for active view selection in X-ray CT that accounts for geometric ambiguities and physical attenuation properties.

Findings

Outperforms existing methods in arbitrary-trajectory CT benchmarks.

Effectively eliminates geometric artifacts in reconstructions.

Enhances progressive tomographic reconstruction quality.

Abstract

Sparse-view computed tomography (CT) is critical for reducing radiation exposure to patients. Recent advances in radiative 3D Gaussian Splatting (3DGS) have enabled fast and accurate sparse-view CT reconstruction. Despite these algorithmic advancements, practical reconstruction fidelity remains fundamentally bounded by the quality of the captured data, raising the crucial yet underexplored problem of X-ray active view selection. Existing active view selection methods are primarily designed for natural-light scenes and fail to capture the unique geometric ambiguities and physical attenuation properties inherent in X-ray imaging. In this paper, we present Perturbed Gaussian Ensemble, an active view selection framework that integrates uncertainty modeling with sequential decision-making, tailored for X-ray Gaussian Splatting. Specifically, we identify low-density Gaussian primitives that are likely to be uncertain and apply stochastic density scaling to construct an ensemble of plausible Gaussian density fields. For each candidate projection, we measure the structural variance of the ensemble predictions and select the one with the highest variance as the next best view. Extensive experimental results on arbitrary-trajectory CT benchmarks demonstrate that our density-guided perturbation strategy effectively eliminates geometric artifacts and consistently outperforms existing baselines in progressive tomographic reconstruction under unified view selection protocols.