X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction

Feiran Wang1,*, Jiachen Tao2,*, Junyi Wu2,*, Haoxuan Wang2, Bin Duan3, Kai Wang4, Zongxin Yang5, Yan Yan2,†
1Illinois Institute of Technology 2University of Illinois Chicago 3Univeristy of Michigan 4National University of Singapore 5Harvard University
*Equal contribution, †Corresponding author
Paper Code arXiv
Comparison of Imaging Processes

(a) Visible light interacts with surfaces mainly through scattering and reflection. NeRF and 3DGS model this by accumulating directional light rays. (b) Rooted in X-rays' attenuation and penetration properties, our X-Field models the radiological density of different materials to reveal internal structure.

Abstract

X-ray imaging is indispensable in medical diagnostics, yet its use is tightly regulated due to potential health risks. To mitigate radiation exposure, recent research focuses on generating novel views from sparse inputs and reconstructing Computed Tomography (CT) volumes, borrowing representations from the 3D reconstruction area. However, these representations originally target visible light imaging that emphasizes reflection and scattering effects, while neglecting penetration and attenuation properties of X-ray imaging. In this paper, we introduce X-Field: , the first 3D representation specifically designed for X-ray imaging, rooted in the energy absorption rates across different materials. To accurately model diverse materials within internal structures, we employ 3D ellipsoids with distinct attenuation coefficients. To estimate each material's energy absorption of X-rays, we devise an efficient path partitioning algorithm accounting for complex ellipsoid intersections. We further propose hybrid progressive initialization to refine the geometric accuracy of X-Filed and incorporate material-based optimization to enhance model fitting along material boundaries. Experiments show that X-Field achieves superior visual fidelity on both real-world human organ and synthetic object datasets, outperforming state-of-the-art methods in X-ray Novel View Synthesis and CT Reconstruction.

Pipeline

Overview of X-Field

(a) Hybrid Progressive Initialization. We begin with X-ray images to construct a coarse initialization using combined iterative methods. (b) Physically Grounded Ellipsoid Representation. We transform initialized ellipsoids into NDC space and associate them with pixels, computing the attenuation integral along the ray considering segment length and ellipsoid intersections. (c) Material-Based Optimization. Our optimization captures detailed materials' boundaries for high-quality rendering.

Foot Scene

Head Scene

Jaw Scene

Teapot Scene

Bonsai Scene

X-ray Novel View Synthesis

X-ray Novel View Synthesis

We present visual examples of reconstructed images across four cases trained with 10 views. Our results demonstrate superior visual quality, richer details, and fewer spatial artifacts. Please zoom in for a closer examination.

CT Reconstruction

CT Reconstruction

Our method produces clearer textures, more refined anatomical structures, and fewer artifacts, particularly in high-contrast regions such as the cranial cavity. Please zoom in for a closer examination.

BibTeX

BibTex Code Here