TY - GEN
T1 - Non-Linear Anisotropic Diffusion for Memory-Efficient Computed Tomography Super-Resolution Reconstruction
AU - Abu Jbara, Khaled F.
AU - Idoughi, Ramzi
AU - Heidrich, Wolfgang
N1 - KAUST Repository Item: Exported on 2021-10-25
Acknowledgements: This work was supported by KAUST as part of the VCC Competitive Funding. The authors would like to thank the anonymous reviewers for their insightful comments, and Ran Tao for helping with the data collection. We also thank Guangming Zang, Prem Chedella and Moetaz Abbas for constructive discussions.
PY - 2021
Y1 - 2021
N2 - Despite the impressive performance of Computed Tomography (CT) hardware, there is still a need to push the boundaries of the CT spatial resolution. Super-resolution techniques have been widely used in computer vision to enhance the resolution of 2D and 3D images. They have also been introduced to improve the CT volume resolution. In this work, we propose a flexible framework that produces a higher-resolution 3D volume from low-resolution 2D projections. This framework can be applied to any CT data regardless of the original physical scale and regardless of the target application. It is based on regularization by denoising (RED) approach, where a Non-Linear Anisotropic Diffusion filter is used as the denoiser. We demonstrate our framework on both simulated and captured data, and show good quality reconstruction and a huge memory-footprint improvement in comparison to the state-of-the-art algorithm.
AB - Despite the impressive performance of Computed Tomography (CT) hardware, there is still a need to push the boundaries of the CT spatial resolution. Super-resolution techniques have been widely used in computer vision to enhance the resolution of 2D and 3D images. They have also been introduced to improve the CT volume resolution. In this work, we propose a flexible framework that produces a higher-resolution 3D volume from low-resolution 2D projections. This framework can be applied to any CT data regardless of the original physical scale and regardless of the target application. It is based on regularization by denoising (RED) approach, where a Non-Linear Anisotropic Diffusion filter is used as the denoiser. We demonstrate our framework on both simulated and captured data, and show good quality reconstruction and a huge memory-footprint improvement in comparison to the state-of-the-art algorithm.
UR - http://hdl.handle.net/10754/672934
UR - https://vccimaging.org/Publications/Abujbara2021NLAD/
M3 - Conference contribution
BT - 2021 International Conference on 3D Vision (3DV)
PB - IEEE
ER -