HuCenLife: Human-centric Scene Understanding in 3D Large-scale Scenarios.

Project Page | Arxiv - ICCV 2023

Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human-environment interactions, severe occlusions in crowds, etc. In this paper, we present a large-scale multi-modal dataset for human-centric scene understanding, named HuCenLife, which is collected in diverse daily-life scenarios with rich and fine-grained annotations. Our HuCenLife can benefit many 3D perception tasks, such as segmentation, detection, action recognition, etc., and we also provide benchmarks for these tasks to facilitate related research. In addition, we design novel modules for LiDAR-based segmentation and action recognition, which are more applicable for large-scale human-centric scenarios and achieve state-of-the-art performance.

🚩 News

Human-centric Scene Understanding in 3D Large-scale Scenarios is accepted at ICCV 2023.

📚 Dataset Download:

Baidu link with extract code: y1zn .

💻 Train your own models

1. Prepare the datasets: please refer to seg_process for processing the instance segmentation annotation.

2. The segmentation result:

• The action recognition result:

License

All datasets are published under the Creative Commons Attribution-NonCommercial-ShareAlike. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.

Citation

@inproceedings{xu2023human, title={Human-centric scene understanding for 3d large-scale scenarios}, author={Xu, Yiteng and Cong, Peishan and Yao, Yichen and Chen, Runnan and Hou, Yuenan and Zhu, Xinge and He, Xuming and Yu, Jingyi and Ma, Yuexin}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={20349--20359}, year={2023} }