Human-centric Scene Understanding for 3D Large-scale Scenarios

TL;DR

This paper introduces HuCenLife, a large-scale multi-modal dataset for human-centric 3D scene understanding, along with novel modules for LiDAR-based segmentation and action recognition that achieve state-of-the-art results.

Contribution

The paper provides a new comprehensive dataset and benchmarks for human-centric 3D scene understanding, and proposes novel modules tailored for large-scale scenarios.

Findings

HuCenLife dataset enables improved 3D perception tasks.

Novel modules outperform existing methods in segmentation and action recognition.

State-of-the-art performance achieved on large-scale human-centric scenarios.

Abstract

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.