Ziwei Liu, Kai Chen, Liang Pan, Xiang Xu, Lingdong Kong, Wenwei Zhang, Hui Shuai, Qingshan Liu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the realm of autonomous driving, accurate 3D perception is the foundation. However, developing such models relies on extensive human annotations -a process that is both costly and labor-intensive. To address this challenge from a data representation learning perspective, we introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing spatiotemporal pretraining objectives. SuperFlow 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 flowbased contrastive learning module, carefully crafted to extract meaningful temporal cues from readily available sensor calibrations. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances the alignment of the knowledge distilled from camera views. Extensive comparative and ablation studies across 11 heterogeneous LiDAR datasets validate our effectiveness and superiority. Additionally, we observe several interesting emerging properties by scaling up the 2D and 3D backbones during pretraining, shedding light on the future research of 3D foundation models for LiDAR-based perception. Code is publicly available at https://github.com/Xiangxu-0103/SuperFlow.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.06190")
get_code_for_paper("2407.06190")
have("2407.06190")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.06190.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.06190)
Connect an agent — have() is free.