bells98 / pointtransformerv3

Official project repository of Point Transformer V3 (PTv3)

Point Transformer V3

This repo is the official project repository of the paper Point Transformer V3: Simpler, Faster, Stronger and is mainly used for releasing schedules, updating instructions, sharing experiments, and handling issues. The code will be updated in Pointcept v1.5.

Highlights

• Dec, 2023: We release of project repo for PTv3, if you have any question related to our work, please feel free to open an issue.

Schedule

To make our polished code and reproduced experiments available as soon as possible, this time we will release what we already finished immediately after a validation instead of releasing them together after all work is done. We list a task list as follows:

• Release model code of PTv3;
• Release scratched config and record of indoor semantic segmentation;
  • ScanNet
  • ScanNet200
  • S3DIS
  • S3DIS 6-Fold (with cross validation script)
• Release pre-trained config and record of indoor semantic segmentation;
  • ScanNet (ScanNet + S3DIS + Structured3D)
  • ScanNet200 (Fine-tuned from above)
  • S3DIS (ScanNet + S3DIS + Structured3D)
  • S3DIS 6-Fold (Fine-tuned from ScanNet + Structured3D)
• Release scratched config and record of outdoor semantic segmentation;
  • NuScenes
  • SemanticKITTI
  • Waymo
• Release pre-trained config and record of outdoor semantic segmentation;
  • NuScenes (NuScenes + SemanticKITTI + Waymo)
  • SemanticKITTI (NuScenes + SemanticKITTI + Waymo)
  • Waymo (NuScenes + SemanticKITTI + Waymo)
• Release config and record of indoor instance segmentation;
  • ScanNet (Scratch and Fine-tuned from PPT pre-trained PTv3)
  • ScanNet200 (Scratch and Fine-tuned from PPT pre-trained PTv3)
• Release config and record of ScanNet data efficient benchmark;
• Release config and record of ImageNet classification;
  • ImageClassifier (making all 3D backbones in Pointcept support image classification)
  • Config and Record (PTv3 + SparseUNet)

Citation

If you find PTv3 useful to your research, please cite our work as an acknowledgment. (੭ˊ꒳​ˋ)੭✧

@inproceedings{wu2022ptv2,
    title={Point transformer V2: Grouped Vector Attention and Partition-based Pooling},
    author={Wu, Xiaoyang and Lao, Yixing and Jiang, Li and Liu, Xihui and Zhao, Hengshuang},
    booktitle={NeurIPS},
    year={2022}
}

@misc{pointcept2023,
    title={Pointcept: A Codebase for Point Cloud Perception Research},
    author={Pointcept Contributors},
    howpublished={\url{https://github.com/Pointcept/Pointcept}},
    year={2023}
}