This repo contains PyTorch implementation for paper DSPDet3D: Dynamic Spatial Pruning for 3D Small Object Detection based on MMDetection3D.

DSPDet3D: Dynamic Spatial Pruning for 3D Small Object Detection
Xiuwei Xu, Zhihao Sun, Ziwei Wang, Hongmin Liu, Jie Zhou, Jiwen Lu

For data preparation and environment setup:

• Installation
• Prepare Dataset

For training and evaluation:

• Train, Eval and Visualize

We provide the checkpoints for quick reproduction of the results reported in the paper. The pruning threshold can be adjusted freely to tradeoff between accuracy and efficiency without any finetuning.

Comparison with state-of-the-art methods on TO-SCENE dataset:

Visualization results on ScanNet dataset:

We thank a lot for the flexible codebase of FCAF3D and valuable datasets provided by ScanNet and TO-SCENE.

If this work is helpful for your research, please consider citing the following BibTeX entry.

@article{xu2023dsp, 
      title={DSPDet3D: Dynamic Spatial Pruning for 3D Small Object Detection}, 
      author={Xiuwei Xu and Zhihao Sun and Ziwei Wang and Hongmin Liu and Jie Zhou and Jiwen Lu},
      journal={arXiv preprint arXiv:xxx},
      year={2023}
}