HICT: High-precision 3D CBCT reconstruction from a single X-ray
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908930843607040 |
|---|---|
| author | Ma, Wen Liu, Jiaxiang Xiao, Zikai Wang, Ziyang Yang, Feng Liu, Zuozhu |
| author_facet | Ma, Wen Liu, Jiaxiang Xiao, Zikai Wang, Ziyang Yang, Feng Liu, Zuozhu |
| contents | Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00792 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HICT: High-precision 3D CBCT reconstruction from a single X-ray Ma, Wen Liu, Jiaxiang Xiao, Zikai Wang, Ziyang Yang, Feng Liu, Zuozhu Computer Vision and Pattern Recognition Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use. |
| title | HICT: High-precision 3D CBCT reconstruction from a single X-ray |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00792 |