HuLiGen: Human LiDAR Generation from Parametric Body Models
In contrast, we introduce HuLiGen, a generative model that generates human LiDAR point clouds from a parametric body model, using a point transformer trained with a flow-matching objective.
Key points
- LiDAR point clouds of humans are extremely expensive to collect and annotate, thus represent a scarce resource that hinders the development of human analysis using this modality.
- To alleviate this scarcity, prior work relies on simulated human LiDAR, but such samples do not fully reflect the geometry and sensing characteristics of real observations.
- We show that our generated point clouds are closer to the real capture distribution.
- Using HuLiGen to generate synthetic data, we propose a synthetic-only pretraining scheme for LiDAR-based HPE that achieves state-of-the-art performance, with even larger gains in low-annotation and low-data regimes, where MPJPE is reduced by up to 50%.
Sources (1)
- [1]HuLiGen: Human LiDAR Generation from Parametric Body ModelsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 02:58 PM
In contrast, we introduce HuLiGen, a generative model that generates human LiDAR point clouds from a parametric body model, using a point transformer trained with a flow-matching objective.
LiDAR point clouds of humans are extremely expensive to collect and annotate, thus represent a scarce resource that hinders the development of human analysis using this modality.
Extractive summary: sentences quoted from the sources.