.png){kind=icon}
返回
Density-Aware Point Cloud Upsampling via Relational Graph Flow Matching
.png){kind=icon}
PRE
AI
DOI：10.1109/LRA.2026.3653291.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Real-world point clouds exhibit non-uniform density distributions, varying across distance and scale. Conventional upsampling methods typically treat points homogeneously, which over-smooths sparse regions while over-processing dense regions. We propose PURF, a density-aware point cloud upsampling framework based on relational graph flow matching. PURF leverages a heterogeneous graph representation to capture density variations through relational graph construction, and employs transformer-based flow matching to predict timestep-dependent velocity fields. This design enables a density-aware and efficient mapping from sparse inputs to dense point clouds, reducing computational overhead compared to recent approaches. Extensive experiments on synthetic, KITTI, and a proprietary campus dataset collected by our team demonstrate that PURF achieves advanced performance in upsampling point clouds qualitatively and quantitatively.
Keyword:
Deep learning for visual perception
computer vision for automation
representation learning
期刊
I
IF:
5.3
论文数:
1.9K
被引数:
3.9W
机构
引用论文
.png){kind=icon}
Towards Dense and Accurate Radar Perception via Efficient Cross-Modal Diffusion Model通过高效跨模态扩散模型实现密集且准确的雷达感知
OAAI
OAAI分享收藏分享收藏
查看更多内容