Home

Awesome

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)

This is the implementation of LargeKernel3D (CVPR 2023). Large kernels are important but expensive in 3D CNNs. We propose spatial-wise partition to conv enable 3D large kernels. High performance on 3D semantic segmentation & object detection. For more details, please refer to:

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs [Paper] <br /> Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia<br />

<p align="center"> <img src="imgs/Large-small-kernels.png" width="100%"> </p>

Experimental results

nuScenes Object DetectionSetmAPNDSDownload
LargeKernel3Dval63.369.1Pre-trained
LargeKernel3Dtest65.470.6Pre-trained Submission
+test augtest68.772.8Submission
LargeKernel3D-Ftest--Pre-trained
+test augtest71.174.2Submission
ScanNetv2 Semantic SegmentationSetmIoUDownload
LargeKernel3Dval73.5[Pre-trained]
LargeKernel3Dtest73.9[Submission]
<p align="center"> <img src="imgs/ReceptiveFields.png" width="100%"> </p>

Citation

If you find this project useful in your research, please consider citing:

@inproceedings{chen2023largekernel3d,
  title={LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs},
  author={Yukang Chen and Jianhui Liu and Xiangyu Zhang and Xiaojuan Qi and Jiaya Jia},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2023}
}

Acknowledgement

Our Works in LiDAR-based 3D Computer Vision

License

This project is released under the Apache 2.0 license.