X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913730307031040 |
|---|---|
| author | Wang, Feiran Tao, Jiachen Wu, Junyi Wang, Haoxuan Duan, Bin Wang, Kai Yang, Zongxin Yan, Yan |
| author_facet | Wang, Feiran Tao, Jiachen Wu, Junyi Wang, Haoxuan Duan, Bin Wang, Kai Yang, Zongxin Yan, Yan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08596 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction Wang, Feiran Tao, Jiachen Wu, Junyi Wang, Haoxuan Duan, Bin Wang, Kai Yang, Zongxin Yan, Yan Computer Vision and Pattern Recognition 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. |
| title | X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08596 |