Human-centric Scene Understanding for 3D Large-scale Scenarios
This work addresses the problem of understanding human activities and interactions in complex 3D environments for applications like robotics and surveillance, though it is incremental as it builds on existing datasets and tasks.
The authors tackled the challenge of human-centric scene understanding in 3D large-scale scenarios by introducing HuCenLife, a large-scale multi-modal dataset with rich annotations, and novel modules for LiDAR-based segmentation and action recognition that achieve state-of-the-art performance.
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, dubbed 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.