Summary of Arkit Labelmaker: a New Scale For Indoor 3d Scene Understanding, by Guangda Ji et al.
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
by Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum
First submitted to arxiv on: 17 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 Transformers have been successfully adapted for 3D vision, but a significant gap remains in terms of training data. To bridge this gap, the authors introduce ARKit LabelMaker, a large-scale real-world 3D dataset with dense semantic annotation that is more than three times larger than the prior largest dataset. By extending ARKitScenes with automatically generated dense 3D labels using an extended LabelMaker pipeline, tailored for large-scale pre-training, the authors demonstrate improved accuracy across architectures and achieve state-of-the-art 3D semantic segmentation scores on ScanNet and ScanNet200, with notable gains on tail classes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a big dataset of 3D pictures with labels that helps computers learn to recognize objects in real-world scenes. The dataset is special because it’s very large and has lots of details about what’s happening in each picture. This makes it easier for computers to learn from the data. The authors also show that using this dataset makes computers better at recognizing things they haven’t seen before. |
Keywords
» Artificial intelligence » Semantic segmentation
