Summary of Food Portion Estimation Via 3d Object Scaling, by Gautham Vinod et al.
Food Portion Estimation via 3D Object Scaling
by Gautham Vinod, Jiangpeng He, Zeman Shao, Fengqing Zhu
First submitted to arxiv on: 18 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multimedia (cs.MM); 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 This paper proposes a novel framework for estimating food volume and energy from 2D images, leveraging 3D food models and physical references in the eating scene. The method estimates camera and food object poses to recreate the eating occasion by rendering a 3D model of the food with estimated poses. The approach outperforms existing portion estimation methods, achieving an average error of 31.10 kCal (17.67%) on the SimpleFood45 dataset. The proposed framework demonstrates improved accuracy in estimating both food volume and energy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how to measure food portions from phone pictures. Right now, we have to guess or use old-fashioned methods that can be biased. But this new approach uses 3D models of food and the way it’s being eaten to get more accurate results. It even has a special dataset with lots of different foods and their measurements. This could help us make better choices about what we eat. |
