Single-View Tomographic Reconstruction Using Learned Primal Dual
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909978549288960 |
|---|---|
| author | Breckling, Sean Swan, Matthew Tan, Keith D. Wingard, Derek Baldonado, Brandon Kim, Yoohwan Jo, Ju-Yeon Scott, Evan Pillow, Jordan |
| author_facet | Breckling, Sean Swan, Matthew Tan, Keith D. Wingard, Derek Baldonado, Brandon Kim, Yoohwan Jo, Ju-Yeon Scott, Evan Pillow, Jordan |
| contents | The Learned Primal Dual (LPD) method has shown promising results in various tomographic reconstruction modalities, particularly under challenging acquisition restrictions such as limited viewing angles or a limited number of views. We investigate the performance of LPD in a more extreme case: single-view tomographic reconstructions of axially-symmetric targets. This study considers two modalities: the first assumes low-divergence or parallel X-rays. The second models a cone-beam X-ray imaging testbed. For both modalities, training data is generated using closed-form integral transforms, or physics-based ray-tracing software, then corrupted with blur and noise. Our results are then compared against common numerical inversion methodologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Single-View Tomographic Reconstruction Using Learned Primal Dual Breckling, Sean Swan, Matthew Tan, Keith D. Wingard, Derek Baldonado, Brandon Kim, Yoohwan Jo, Ju-Yeon Scott, Evan Pillow, Jordan Image and Video Processing The Learned Primal Dual (LPD) method has shown promising results in various tomographic reconstruction modalities, particularly under challenging acquisition restrictions such as limited viewing angles or a limited number of views. We investigate the performance of LPD in a more extreme case: single-view tomographic reconstructions of axially-symmetric targets. This study considers two modalities: the first assumes low-divergence or parallel X-rays. The second models a cone-beam X-ray imaging testbed. For both modalities, training data is generated using closed-form integral transforms, or physics-based ray-tracing software, then corrupted with blur and noise. Our results are then compared against common numerical inversion methodologies. |
| title | Single-View Tomographic Reconstruction Using Learned Primal Dual |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2512.16065 |