Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar Consistency Conditions

TL;DR

Epi-NAF introduces an epipolar consistency loss to improve neural attenuation field-based limited-angle CT reconstruction, enabling better image quality by leveraging geometric constraints across projections.

Contribution

The paper proposes a novel epipolar consistency loss that enhances neural field methods for limited-angle CT reconstruction, addressing a key challenge in the field.

Findings

Significant qualitative improvements in reconstructed images.

Quantitative gains over baseline methods in accuracy.

Effective propagation of supervision across limited-angle projections.

Abstract

Neural field methods, initially successful in the inverse rendering domain, have recently been extended to CT reconstruction, marking a paradigm shift from traditional techniques. While these approaches deliver state-of-the-art results in sparse-view CT reconstruction, they struggle in limited-angle settings, where input projections are captured over a restricted angle range. We present a novel loss term based on consistency conditions between corresponding epipolar lines in X-ray projection images, aimed at regularizing neural attenuation field optimization. By enforcing these consistency conditions, our approach, Epi-NAF, propagates supervision from input views within the limited-angle range to predicted projections over the full cone-beam CT range. This loss results in both qualitative and quantitative improvements in reconstruction compared to baseline methods.