X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yifan, Li, Wuyang, Yu, Weihao, Li, Chenxin, Alahi, Alexandre, Meng, Max, Yuan, Yixuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909622966681600
author Liu, Yifan
Li, Wuyang
Yu, Weihao
Li, Chenxin
Alahi, Alexandre
Meng, Max
Yuan, Yixuan
author_facet Liu, Yifan
Li, Wuyang
Yu, Weihao
Li, Chenxin
Alahi, Alexandre
Meng, Max
Yuan, Yixuan
contents Computed Tomography serves as an indispensable tool in clinical workflows, providing non-invasive visualization of internal anatomical structures. Existing CT reconstruction works are limited to small-capacity model architecture and inflexible volume representation. In this work, we present X-GRM (X-ray Gaussian Reconstruction Model), a large feedforward model for reconstructing 3D CT volumes from sparse-view 2D X-ray projections. X-GRM employs a scalable transformer-based architecture to encode sparse-view X-ray inputs, where tokens from different views are integrated efficiently. Then, these tokens are decoded into a novel volume representation, named Voxel-based Gaussian Splatting (VoxGS), which enables efficient CT volume extraction and differentiable X-ray rendering. This combination of a high-capacity model and flexible volume representation, empowers our model to produce high-quality reconstructions from various testing inputs, including in-domain and out-domain X-ray projections. Our codes are available at: https://github.com/CUHK-AIM-Group/X-GRM.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15235
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography
Liu, Yifan
Li, Wuyang
Yu, Weihao
Li, Chenxin
Alahi, Alexandre
Meng, Max
Yuan, Yixuan
Image and Video Processing
Computer Vision and Pattern Recognition
Computed Tomography serves as an indispensable tool in clinical workflows, providing non-invasive visualization of internal anatomical structures. Existing CT reconstruction works are limited to small-capacity model architecture and inflexible volume representation. In this work, we present X-GRM (X-ray Gaussian Reconstruction Model), a large feedforward model for reconstructing 3D CT volumes from sparse-view 2D X-ray projections. X-GRM employs a scalable transformer-based architecture to encode sparse-view X-ray inputs, where tokens from different views are integrated efficiently. Then, these tokens are decoded into a novel volume representation, named Voxel-based Gaussian Splatting (VoxGS), which enables efficient CT volume extraction and differentiable X-ray rendering. This combination of a high-capacity model and flexible volume representation, empowers our model to produce high-quality reconstructions from various testing inputs, including in-domain and out-domain X-ray projections. Our codes are available at: https://github.com/CUHK-AIM-Group/X-GRM.
title X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15235