Summary of Score-based Multibeam Point Cloud Denoising, by Li Ling et al.
Score-Based Multibeam Point Cloud Denoising
by Li Ling, Yiping Xie, Nils Bore, John Folkesson
First submitted to arxiv on: 20 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 A novel approach to bathymetry mapping using multibeam echo-sounders (MBES) is presented in this paper. The growth of MBES data has been exponential due to cheaper sensors and global initiatives. However, raw MBES data contains noise that requires semi-automatic filtering, typically done with tools like the Combined Uncertainty and Bathymetric Estimator (CUBE). Inspired by 3D point cloud denoising networks, the authors adapted a score-based network for MBES outlier detection and denoising. The network was trained and evaluated on real MBES survey data, outperforming classical methods. This approach can be integrated into existing MBES standard workflows. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses special sensors to map the ocean floor. There’s a lot of data available now because these sensors are cheaper and there are more initiatives to collect it. The problem is that this data has some mistakes in it, like noise. Usually, people use tools to clean up this noise. This paper takes inspiration from how people clean up mistakes in 3D pictures and applies it to ocean floor mapping. They tested their method on real data and it worked better than the usual way of doing things. |
Keywords
» Artificial intelligence » Outlier detection
