Non-Linear Anisotropic Diffusion for Memory-Efficient Computed Tomography Super-Resolution Reconstruction

Khaled Abujbara*, Ramzi Idoughi*, Wolfgang Heidrich
(* Joint first authors)
3DV 2021 (Oral)


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.

Our super-resolution CT reconstruction method tackles thin structures beyond the Nyquist limit of the image sensor, including thin fibrous features such as the toothbrush (top) and jute ball (middle), as well as thin surface features such as the folding paper fan (bottom). From left to right: camera photo, x-ray image, and 3D reconstruction.


paper [AbuJbara_2021_NLAD.pdf] 
supplemental material [AbuJbara_2021_NLAD_supplementary.pdf]

Code and Dataset

Source code  [Code  (coming soon)] 

Dataset  [Dataset (coming soon)] 


      title={Non-Linear Anisotropic Diffusion for Memory-Efficient Computed Tomography Super-Resolution Reconstruction}, 
      author={AbuJbara, Khaled and Idoughi, Ramzi and Heidrich, Wolfgang},  
      booktitle = {2021 International Conference on 3D Vision (3DV)}, 
      year = {2021},