[CVPR 2024] Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Zhaochong An, Guolei Sun^†, Yun Liu^†, Fayao Liu, Zongwei Wu, Dan Wang, Luc Van Gool, Serge Belongie

Welcome to the official PyTorch implementation repository of our paper Rethinking Few-shot 3D Point Cloud Semantic Segmentation, accepted to CVPR 2024 [arXiv].

Highlight

The first thing we want you to be aware from this paper:

please ensure you are using our corrected setting for the development and evaluation of your 3D few-shot models.

---

1. Identification of Key Issues: We pinpoint two significant issues in the current Few-shot 3D Point Cloud Semantic Segmentation (FS-PCS) setting: foreground leakage and sparse point distribution. These issues have undermined the validity of previous progress and hindered further advancements.
2. Standardized Setting and Benchmark: To rectify existing issues, we propose a standardized FS-PCS setting along with a new benchmark. This enables fair comparisons and fosters future advancements in the field. Our repository implements an effective few-shot running pipeline on our proposed standard FS-PCS setting, facilitating easy development for future researchers based on our code base.

3. Novel Method (COSeg): Our method introduces a novel correlation optimization paradigm, diverging from the traditional feature optimization approach used by all previous FS-PCS models. COSeg achieves state-of-the-art performance on both S3DIS and ScanNetv2 datasets, demonstrating effective contextual learning and background correlation adjustment ability.

Get Started

Environment

The following environment setup instructions have been tested on RTX 3090 GPUs with GCC 6.3.0.

1. Install dependencies

pip install -r requirements.txt

If you have any problem with the above command, you can also install them by

pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
pip install torch_points3d==1.3.0
pip install torch-scatter==2.1.1
pip install torch-points-kernels==0.6.10
pip install torch-geometric==1.7.2
pip install timm==0.9.2
pip install tensorboardX==2.6
pip install numpy==1.20.3

2. Compile pointops

Ensure you have gcc, cuda, and nvcc installed. Compile and install pointops2 as follows:

cd lib/pointops2
python3 setup.py install

Datasets Preparation

You can either directly download the preprocessed dataset directly from the links provided below or perform the preprocessing steps on your own.

Preprocessed Datasets

Dataset	Download
S3DIS	Download link
ScanNet	Download link

Preprocessing Instructions

S3DIS

1. Download: S3DIS Dataset Version 1.2.
2. Preprocessing: Re-organize raw data into npy files:

   cd preprocess
   python collect_s3dis_data.py --data_path [PATH_to_S3DIS_raw_data] --save_path [PATH_to_S3DIS_processed_data]

   The generated numpy files will be stored in PATH_to_S3DIS_processed_data/scenes.
3. Splitting Rooms into Blocks:

   python room2blocks.py --data_path [PATH_to_S3DIS_processed_data]/scenes

ScanNet

1. Download: ScanNet V2.
2. Preprocessing: Re-organize raw data into npy files:

   cd preprocess
   python collect_scannet_data.py --data_path [PATH_to_ScanNet_raw_data] --save_path [PATH_to_ScanNet_processed_data]

   The generated numpy files will be stored in PATH_to_ScanNet_processed_data/scenes.
3. Splitting Rooms into Blocks:

   python room2blocks.py --data_path [PATH_to_ScanNet_processed_data]/scenes

After preprocessing the datasets, a folder named blocks_bs1_s1 will be generated under PATH_to_DATASET_processed_data. Make sure to update the data_root entry in the .yaml config file to [PATH_to_DATASET_processed_data]/blocks_bs1_s1/data.

Model weights

We provide the trained model weights across different few-shot settings and datasets below. The training and testing are using 4 RTX 3090 GPUs. Please note that these weights have been retrained by us, which may have slight differences from reported results. You could directly load these weights for evaluation or train your own models following the training instructions.

Model name	Dataset	CVFOLD	N-way K-shot	Model Weight
s30_1w1s	S3DIS	0	1-way 1-shot	Download link
s30_1w5s	S3DIS	0	1-way 5-shot	Download link
s30_2w1s	S3DIS	0	2-way 1-shot	Download link
s30_2w5s	S3DIS	0	2-way 5-shot	Download link
s31_1w1s	S3DIS	1	1-way 1-shot	Download link
s31_1w5s	S3DIS	1	1-way 5-shot	Download link
s31_2w1s	S3DIS	1	2-way 1-shot	Download link
s31_2w5s	S3DIS	1	2-way 5-shot	Download link
sc0_1w1s	ScanNet	0	1-way 1-shot	Download link
sc0_1w5s	ScanNet	0	1-way 5-shot	Download link
sc0_2w1s	ScanNet	0	2-way 1-shot	Download link
sc0_2w5s	ScanNet	0	2-way 5-shot	Download link
sc1_1w1s	ScanNet	1	1-way 1-shot	Download link
sc1_1w5s	ScanNet	1	1-way 5-shot	Download link
sc1_2w1s	ScanNet	1	2-way 1-shot	Download link
sc1_2w5s	ScanNet	1	2-way 5-shot	Download link

Backbone pretraining

To begin, you will need to pretrain the backbone either on the S3DIS or ScanNet dataset. For consistency and ease of reproduction, we highly recommend using our pretrained backbone weights directly. You can find the pretrained weights and their corresponding download links below:

Model name	Dataset	CVFOLD	Model Weight
s3_s1pre	S3DIS	1	Download link
s3_s0pre	S3DIS	0	Download link
sc_s1pre	ScanNet	1	Download link
sc_s0pre	ScanNet	0	Download link

Alternatively, you can perform the pretraining on your own. However, please note that doing so may result in more variability compared to the results reported in our paper.

To pretrain the backbone from scratch, run the following command, replacing [PRETRAIN_CONFIG] with the respective configuration file (s3dis_stratified_pretraining.yaml or scannetv2_stratified_pretraining.yaml), [PATH_to_SAVE_BACKBONE] with the desired path to save the backbone, and [CVFOLD] with either 0 or 1 depending on your few-shot setting:

python3 train_backbone.py --config config/[PRETRAIN_CONFIG] save_path [PATH_to_SAVE_BACKBONE] cvfold [CVFOLD]

Few-shot Training

Next, let us start the few-shot training. Set the configs in config/[CONFIG_FILE] (s3dis_COSeg_fs.yaml or scannetv2_COSeg_fs.yaml) for few-shot training. Adjust cvfold, n_way, and k_shot according to your task:

# 1 way 1/5 shot
python3 main_fs.py --config config/[CONFIG_FILE] save_path [PATH_to_SAVE_MODEL] pretrain_backbone [PATH_to_SAVED_BACKBONE] cvfold [CVFOLD] n_way 1 k_shot [K_SHOT] num_episode_per_comb 1000
# 2 way 1/5 shot
python3 main_fs.py --config config/[CONFIG_FILE] save_path [PATH_to_SAVE_MODEL] pretrain_backbone [PATH_to_SAVED_BACKBONE] cvfold [CVFOLD] n_way 2 k_shot [K_SHOT] num_episode_per_comb 100

Note: By default, when n_way=1, num_episode_per_comb is set to 1000. When n_way=2, num_episode_per_comb is adjusted to 100 to maintain consistency in test set magnitude.

Testing

For testing, modify cvfold, n_way, k_shot and num_episode_per_comb accordingly, then run:

python3 main_fs.py --config config/[CONFIG_FILE] test True eval_split test weight [PATH_to_SAVED_MODEL]

For visualization, add vis 1.

Note: It is common to observe fluctuations in the mIoU by approximately 1.0%. This variability may be attributed to the relatively small size of the training set. The variance in performance on ScanNetv2 tends to be smaller compared to S3DIS due to its larger size. Additionally, the mean performance across the two dataset splits is generally more stable than the performance of each split individually.

Citation

If you find this project useful, please consider giving a star ⭐ and citation 📚:

@article{an2024rethinking,
  title={Rethinking Few-shot 3D Point Cloud Semantic Segmentation},
  author={An, Zhaochong and Sun, Guolei and Liu, Yun and Liu, Fayao and Wu, Zongwei and Wang, Dan and Van Gool, Luc and Belongie, Serge},
  journal={arXiv preprint arXiv:2403.00592},
  year={2024}
}

For any questions or issues, feel free to reach out!

Zhaochong An: [email protected]

Communication Group: