Summary of Nerf-us: Removing Ultrasound Imaging Artifacts From Neural Radiance Fields in the Wild, by Rishit Dagli et al.
NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild
by Rishit Dagli, Atsuhiro Hibi, Rahul G. Krishnan, Pascal N. Tyrrell
First submitted to arxiv on: 13 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 This paper introduces NeRF-US, a novel approach for 3D reconstruction and novel view synthesis (NVS) in ultrasound imaging data. Current methods face severe artifacts when training NeRF-based approaches, particularly in ultrasound data captured casually in uncontrolled environments, which is common in clinical settings. The authors incorporate 3D-geometry guidance for border probability and scattering density into NeRF training, utilizing ultrasound-specific rendering over traditional volume rendering. This approach learns 3D priors through a diffusion model and is evaluated on the “Ultrasound in the Wild” dataset, demonstrating accurate, clinically plausible, artifact-free reconstructions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a big problem in medical imaging. Right now, it’s hard to create 3D images from ultrasound data because of distortions and artifacts. The authors developed a new way called NeRF-US that helps fix these issues. They used special training methods and a unique dataset to make sure the results are accurate and realistic. This is important because it will help doctors get better pictures from ultrasound scans, which can be used for diagnosis and treatment. |
Keywords
» Artificial intelligence » Diffusion model » Probability
