Summary of Glimpse: Generalized Local Imaging with Mlps, by Amirehsan Khorashadizadeh et al.
GLIMPSE: Generalized Local Imaging with MLPs
by AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmanić
First submitted to arxiv on: 1 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces GLIMPSE, a local processing neural network for computed tomography (CT) that reconstructs pixel values by feeding only the measurements associated with the neighborhood of the pixel to a simple multi-layer perceptron (MLP). This approach addresses the limitations of current deep learning-based CT reconstruction methods, which require large receptive fields and overfit to global structures. GLIMPSE achieves comparable or better performance on in-distribution test data while significantly outperforming them on out-of-distribution samples. The model is fully differentiable, enabling applications such as recovering accurate projection angles if they are out of calibration. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way for computers to make pictures from CT scans using artificial intelligence. Instead of looking at all the scan data at once, it only looks at the parts that matter for each tiny piece of the picture. This makes the computer’s job easier and more accurate. The new method is also better at making good pictures when the scan data doesn’t quite match what the computer was trained on. |
Keywords
* Artificial intelligence * Deep learning * Neural network
