Home

Awesome

LidarCLIP

This is the official implementation of the WACV 2024 paper LidarCLIP or: How I Learned to Talk to Point Clouds.

LidarCLIP overview

Checkpoints

CLIP VersionTraining DatasetLink
ViT-L/14ONCEgoogle drive
ViT-B/32ONCEgoogle drive

Instructions

Note that some paths have to be modified in the notebooks to point your desired dataset and cached features.

Dataset preparation

We refer to the official download and preparation instructions for ONCE and NuScenes. For ONCE, you'll also need the ImageSets folder from the ONCE devkit. Once the dataset directories are set up according to the official instructions, our code works without any additional steps. Note that NuScenes is entirely optional and only used for evaluating domain shift capabilities.

Citation

If you find this work useful, please cite

@inproceedings{lidarclip2024,
  title={LidarCLIP or: How I Learned to Talk to Point Clouds},
  author={Hess, Georg and Tonderski, Adam and Petersson, Christoffer and {\AA}str{\"o}m, Kalle} and Svensson, Lennart,
  year = {2024},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
}