ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding

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 atthis https URLand our dataset atthis https URL.

@article{ji2025_2410.13924,
  title={ ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding },
  author={ Guangda Ji and Silvan Weder and Francis Engelmann and Marc Pollefeys and Hermann Blum },
  journal={arXiv preprint arXiv:2410.13924},
  year={ 2025 }
}