Liang Pan2, Kai Chen2, Ziwei Liu5, Qingshan Liu4
1Nanjing University of Aeronautics and Astronautics 2Shanghai AI Laboratory 3National University of Singapore 4Nanjing University of Posts and Telecommunications 5S-Lab, Nanyang Technological University
SuperFlow is introduced to harness consecutive LiDAR-camera pairs for establishing spatiotemporal pretraining objectives. It stands out by integrating two key designs: 1) a dense-to-sparse consistency regularization, which promotes insensitivity to point cloud density variations during feature learning, and 2) a flow-based contrastive learning module, carefully crafted to extract meaningful temporal cues from readily available sensor calibrations.
- [2024.07] - Our paper is accepted by ECCV.
For details related to installation and environment setups, kindly refer to INSTALL.md.
Kindly refer to DATA_PREPAER.md for the details to prepare the datasets.
To learn more usage about this codebase, kindly refer to GET_STARTED.md.
This work is under the Apache 2.0 license.
If you find this work helpful for your research, please kindly consider citing our paper:
@inproceedings{xu2024superflow,
title = {4D Contrastive Superflows are Dense 3D Representation Learners},
author = {Xu, Xiang and Kong, Lingdong and Shuai, Hui and Zhang, Wenwei and Pan, Liang and Chen, Kai and Liu, Ziwei and Liu, Qingshan},
booktitle = {European Conference on Computer Vision},
year = {2024}
}
This work is developed based on the MMDetection3D codebase.
MMDetection3D is an open-source object detection toolbox based on PyTorch, towards the next-generation platform for general 3D perception. It is a part of the OpenMMLab project developed by MMLab.
We acknowledge the use of the following public resources during the couuse of this work: 1nuScenes, 2nuScenes-devkit, 3SemanticKITTI, 4SemanticKITTI-API, , 5WaymoOpenDataset, 6Synth4D, 7ScribbleKITTI, 8RELLIS-3D, 9SemanticPOSS, 10SemanticSTF, 11SynthLiDAR, 12DAPS-3D, 13Robo3D, 14SLidR, 15DINOv2, 16Segment-Any-Point-Cloud, 17OpenSeeD, 18torchsparse. 💟