Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
| Date | Stars |
|---|---|
| 2026-07-24 | 735 |
| 2026-07-25 | 736 |
| 2026-07-28 | 737 |
| 2026-07-30 | 737 |
| 2026-08-06 | 737 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## Mask3D: Mask Transformer for 3D Instance Segmentation <div align="center"> <a href="https://jonasschult.github.io/">Jonas Schult</a><sup>1</sup>, <a href="https://francisengelmann.github.io/">Francis Engelmann</a><sup>2,3</sup>, <a href="https://www.vision.rwth-aachen.de/person/10/">Alexander Hermans</a><sup>1</sup>, <a href="https://orlitany.github.io/">Or Litany</a><sup>4</sup>, <a href="https://inf.ethz.ch/people/person-detail.MjYyNzgw.TGlzdC8zMDQsLTg3NDc3NjI0MQ==.html">Siyu Tang</a><sup>3</sup>, <a href="https://www.vision.rwth-aachen.de/person/1/">Bastian Leibe</a><sup>1</sup> <sup>1</sup>RWTH Aachen University <sup>2</sup>ETH AI Center <sup>3</sup>ETH Zurich <sup>4</sup>NVIDIA Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D. [](https://paperswithcode.com/sota/3d-instance-segmentation-on-scannetv2?p=mask3d-for-3d-semantic-instance-segmentation) [](https://paperswithcode.com/sota/3d-instance-segmentation-on-scannet200?p=mask3d-for-3d-semantic-instance-segmentation) [](https://paperswithcode.com/sota/3d-instance-segmentation-on-s3dis?p=mask3d-for-3d-semantic-instance-segmentation) [](https://paperswithcode.com/sota/3d-instance-segmentation-on-stpls3d?p=mask3d-for-3d-semantic-instance-segmentation) <a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"></a> <a href="https://pytorchlightning.ai/"><img alt="Lightning" src="https://img.shields.io/badge/-Lightning-792ee5?logo=pytorchlightning&logoColor=white"></a> <a href="https://hydra.cc/"><img alt="Config: Hydra" src="https://img.shields.io/badge/Config-Hydra-89b8cd"></a>  </div> <br><br> [[Project Webpage](https://jonasschult.github.io/Mask3D/)] [[Paper](https://arxiv.org/abs/2210.03105)] [[Demo](https://francisengelmann.github.io/mask3d/)] ## News * **29. October 2023**: Check out this [easy setup](https://github.com/cvg/Mask3D) for Mask3D. * **17. January 2023**: Mask3D is accepted at ICRA 2023. :fire: * **14. October 2022**: STPLS3D support added. * **10. October 2022**: Mask3D ranks 2nd on the [STPLS3D Challenge](https://codalab.lisn.upsaclay.fr/competitions/4646#results) hosted by the [Urban3D Workshop](https://urban3dchallenge.github.io/) at ECCV 2022. * **6. October 2022**: [Mask3D preprint](https://arxiv.org/abs/2210.03105) released on arXiv. * **25. September 2022**: Code released. ## Code structure We adapt the codebase of [Mix3D](https://github.com/kumuji/mix3d) which provides a highly modularized framework for 3D Semantic Segmentation based on the MinkowskiEngine. ``` ├── mix3d │ ├── main_instance_segmentation.py <- the main file │ ├── conf <- hydra configuration files │ ├── datasets │ │ ├── preprocessing <- folder with preprocessing scripts │ │ ├── semseg.py <- indoor dataset │ │ └── utils.py │ ├── models <- Mask3D modules │ ├── trainer │ │ ├── __init__.py │ │ └── trainer.py <- train loop │ └── utils ├── data │ ├── processed <- folder for preprocessed datasets │ └── raw <- folder for raw datasets ├── scripts <- train scrip
Excerpt of 16,249 characters
Read on GitHub
51
2
Ikko Eltociear Ashimine · Japan
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4996da7342fcc742, topic:deep-learning, topic:pytorch
matched fp:4996da7342fcc742, topic:computer-vision, readme:semantic segmentation, readme:instance segmentation