Summary of Learning to Find Missing Video Frames with Synthetic Data Augmentation: a General Framework and Application in Generating Thermal Images Using Rgb Cameras, by Mathias Viborg Andersen et al.
Learning to Find Missing Video Frames with Synthetic Data Augmentation: A General Framework and Application in Generating Thermal Images Using RGB Cameras
by Mathias Viborg Andersen, Ross Greer, Andreas Møgelmose, Mohan Trivedi
First submitted to arxiv on: 29 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 The proposed generative model approach uses conditional generative adversarial networks (cGANs) to create synthetic yet realistic thermal imagery, addressing the issue of missing data due to sensor frame rate mismatches in Advanced Driver Assistance Systems (ADAS). The study compares pix2pix and CycleGAN architectures, finding that pix2pix outperforms CycleGAN. Additionally, utilizing multi-view input styles, especially stacked views, enhances the accuracy of thermal image generation. The model’s generalizability across different subjects is evaluated, revealing the importance of individualized training for optimal performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create more accurate and complete images of drivers inside vehicles, which can improve how well cars understand what the driver is doing. It uses special computer models to fill in gaps where there isn’t enough data because sensors are working at different speeds. The study found that one type of model works better than another, and that using multiple views makes it more accurate. It also shows that training the model on specific people makes it work better. |
Keywords
* Artificial intelligence * Generative model * Image generation
