Easy and flexible imaging with the Core Imaging...
summary
Core Imaging Library (CIL) is an open‑source Python toolkit that claims to reproduce near‑math formulations of large‑scale imaging inverse problems and actually reconstructs real tomographic data. Demos show deblurring, inpainting and laminography reconstructions using FISTA and PDHG, plug‑in fidelities (L2 L1 KL) and regularizers including Tikhonov, total variation and TGV. GPU backends such as the astra toolbox and a tcre interface speed up projections; results reduce streak artifacts and recover large edges though small features remain challenging.
AI-written summary · about
chapters (12)
- 0:00Intro
- 0:46What is the Core Imaging Library (CIL)?
- 2:35What is an Inverse Problem?
- 3:24Imaging Examples : Deblurring
- 3:55Imaging Examples: Inpainting
- 4:26Imaging Examples: Computed Tomography
- 8:32How to solve an inverse problem?
- 11:11Model an inverse problem with CIL - fidelity
- 12:36Model an inverse problem with CIL - optim. algorithm
- 21:32CIL for X-Ray Computed Tomography (CT)
- 33:23Fast time-resolved tomography - directional TV with CIL
- 36:53Training events
related talks
01h 26mITK in Biomedical Research and Commercial Applications
28mNot a long time ago, in a galaxy not very far away, an astronomer and a computer scientist walk into
31mPainting with Python
24mImage recognition and camera positioning with OpenCV. A tourist guide application.
52mKeynote: Learning programming and science with Scientific Python
35mFast Multidimensional Signal Processing using Julia with Shearlab.jl
16mLung Biopsy: Python's Cut Above the Rest (Minus the Actual Cut)
31mOpenDataCube - Petabyte Scale Satellite Imagery Processing in Python