# RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration

Source: [RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T10:56:48.857Z

Authors: Ao Shen, Xueming Fu, Junfeng Jiang, Qiang Zeng, Ye Tang, Zhengming Chen, Luming Nong, Feng Wang, S. Kevin Zhou

Published: 2025-08-28T18:40:13.000Z

## Abstract

Computed Tomography (CT)/X-ray registration in image-guided navigation remains challenging because of its stringent requirements for high accuracy and real-time performance. Traditional "render and compare" methods, relying on iterative projection and comparison, suffer from spatial information loss and domain gap. 3D reconstruction from biplanar X-rays supplements spatial and shape information for 2D/3D registration, but current methods are limited by dense-view requirements and struggles with noisy X-rays. To address these limitations, we introduce RadGS-Reg, a novel framework for vertebral-level CT/X-ray registration through joint 3D Radiative Gaussians (RadGS) reconstruction and 3D/3D registration. Specifically, our biplanar X-rays vertebral RadGS reconstruction module explores learning-based RadGS reconstruction method with a Counterfactual Attention Learning (CAL) mechanism, focusing on vertebral regions in noisy X-rays. Additionally, a patient-specific pre-training strategy progressively adapts the RadGS-Reg from simulated to real data while simultaneously learning vertebral shape prior knowledge. Experiments on in-house datasets demonstrate the state-of-the-art performance for both tasks, surpassing existing methods. The code is available at: https://github.com/shenao1995/RadGS\_Reg.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Reconstruction on In-house Real X-ray Dataset (test)](<https://www.sota2.com/research/sota/3d-reconstruction-on-in-house-real-x-ray-dataset-test.md>): 3D Reconstruction; In-house Real X-ray Dataset (test); SSIM: 0.9451.

- [2D/3D Registration on In-house Real X-ray Dataset (test)](<https://www.sota2.com/research/sota/2d-3d-registration-on-in-house-real-x-ray-dataset-test.md>): 2D/3D Registration; In-house Real X-ray Dataset (test); mTRE (mm): 1.14.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.21154>)

[PDF](<https://arxiv.org/pdf/2508.21154.pdf>)

[Implementation](<https://www.sota2.com/github.com/shenao1995/RadGS_Reg>)