Goal
LiDAR Human Motion project is jointly promoted by spAital Sensing and Computing Lab, Xiamen University and Shanghai Engineering Research Center of Intelligent Vision and Imaging, ShanghaiTech University. Our goal is to capture, perceive and understand the human, scenes, and the interactions between humans and scenes in the complex real world, and finally create a dynamic 4D digital world!
LiDAR is appearance-unaware and privacy-preserved, can acquire accurate 3D positions, and has a longer range scanning area than the conventional Motion Capture equipment.
News
09 / 2024 HiSC4D accepted by TPAMI 2024.
06 / 2024 ASC Lab participate CVPR2024 in Seattle, USA!
06 / 2024 RELI11D is available.
02 / 2024 RELI11D accepted by CVPR 2024.
06 / 2023 ASC Lab participate CVPR2023 in Vancouver, Canada!
06 / 2023 SLOPER4D and CIMI4D are available.
02 / 2023 SLOPER4D and CIMI4D accepted by CVPR 2023.
04 / 2022 We published two dataset, HSC4D and LiDARHuman26M.
03 / 2022 HSC4D and LiDARCap accepted by CVPR 2022
Selected Publication
2024
We introduce HiSC4D, a novel Human-centered interaction and 4D Scene Capture method, aimed at accurately and efficiently creating a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, rich human-human interactions, and human-environment interactions. By utilizing body-mounted IMUs and a head-mounted LiDAR, HiSC4D can capture egocentric human motions in unconstrained space without the need for external devices and pre-built maps. …
Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB, LiDAR, or IMU data. However, solely using these modalities or a combination of them may not be adequate for HPE, particularly for complex and fast movements. …
2023
We present SLOPER4D, a novel scene-aware dataset collected in large urban environments to facilitate the research of global human pose estimation (GHPE) with human-scene interaction in the wild. Employing a head-mounted device integrated with a LiDAR and camera, we record 12 human subjects’ activities over 10 diverse urban scenes from an egocentric view. …
We collect CIMI4D, a large rock ClImbing MotIon dataset from 12 persons climbing 13 different climbing walls. The dataset consists of around 180,000 frames of pose inertial measurements, LiDAR point clouds, RGB videos, high-precision static point cloud scenes, and reconstructed scene meshes. …
2022
HSC4D is a Human-centered 4D Scene Capture to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments. Using only body …
Existing motion capture datasets are largely short-range and cannot yet fit the need of long-range applications. We propose LiDARHuman26M, a new human motion capture dataset captured by LiDAR at a much longer range to overcome this limitation …