ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913746594562048 |
|---|---|
| author | Ji, Guangda Weder, Silvan Engelmann, Francis Pollefeys, Marc Blum, Hermann |
| author_facet | Ji, Guangda Weder, Silvan Engelmann, Francis Pollefeys, Marc Blum, Hermann |
| contents | Neural network performance scales with both model size and data volume, as shown in both language and image processing. This requires scaling-friendly architectures and large datasets. While transformers have been adapted for 3D vision, a `GPT-moment' remains elusive due to limited training data. We introduce ARKit LabelMaker, a large-scale real-world 3D dataset with dense semantic annotation that is more than three times larger than prior largest dataset. Specifically, we extend ARKitScenes with automatically generated dense 3D labels using an extended LabelMaker pipeline, tailored for large-scale pre-training. Training on our dataset improves accuracy across architectures, achieving state-of-the-art 3D semantic segmentation scores on ScanNet and ScanNet200, with notable gains on tail classes. Our code is available at https://labelmaker.org and our dataset at https://huggingface.co/datasets/labelmaker/arkit_labelmaker. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13924 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding Ji, Guangda Weder, Silvan Engelmann, Francis Pollefeys, Marc Blum, Hermann Computer Vision and Pattern Recognition Artificial Intelligence Neural network performance scales with both model size and data volume, as shown in both language and image processing. This requires scaling-friendly architectures and large datasets. While transformers have been adapted for 3D vision, a `GPT-moment' remains elusive due to limited training data. We introduce ARKit LabelMaker, a large-scale real-world 3D dataset with dense semantic annotation that is more than three times larger than prior largest dataset. Specifically, we extend ARKitScenes with automatically generated dense 3D labels using an extended LabelMaker pipeline, tailored for large-scale pre-training. Training on our dataset improves accuracy across architectures, achieving state-of-the-art 3D semantic segmentation scores on ScanNet and ScanNet200, with notable gains on tail classes. Our code is available at https://labelmaker.org and our dataset at https://huggingface.co/datasets/labelmaker/arkit_labelmaker. |
| title | ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.13924 |