高斯密度溅射网络
Gaussian Density Splatting Network
Miao Shang · Yabin Wang · Xiaopeng Hong
中文摘要
提出一种新的人群计数方法 GDSNet (Gaussian Density Splatting Network)。与依赖传统网格密度图、对空间分辨率敏感的方法不同，GDSNet 将人群表示为连续 2D 高斯基元的叠加。两个核心贡献:其一,引入基于控制点的拟合机制来组织高斯参数预测,设计一套方法分配控制点以定义局部区域,从这些区域池化特征回归每个基元的参数;其二,将可微分高斯溅射 (Differentiable Gaussian Splatting) 框架适配到计数任务中,每个基元由几何参数与一个标量密度质量参数化,通过可微分渲染的密度图进行空间匹配实现端到端训练,自然同时提供局部密度监督与全局计数优化。在 4 个标准基准上的大量评测显示 GDSNet 一致优于当前最优方法。
关键要点
- 01问题:传统基于网格密度图的人群计数方法对空间分辨率敏感
- 02方法:将人群表示为连续 2D 高斯基元叠加,通过控制点机制分配局部区域并池化特征回归基元参数
- 03方法:借鉴可微分高斯溅射框架,以几何参数+标量密度质量参数化每个基元,端到端训练
- 04结果:在 4 个标准基准上一致优于当前最优方法
- 05价值:同时提供局部密度监督与全局计数优化
解读
尚无解读。
原始英文摘要
arXiv:2610.10396v1 Announce Type: new Abstract: This paper proposes a novel crowd counting approach, the Gaussian Density Splatting Network (GDSNet). Unlike methods that rely on conventional, grid-based density maps and are sensitive to spatial resolution, GDSNet represents a crowd as a superposition of continuous 2D Gaussian primitives. Our approach is built upon two key contributions. First, we introduce a control-point-based fitting mechanism to structure the prediction of the Gaussian parameters. We design a method to allocate a set of control points that define local regions, from which features are pooled to regress each primitive's parameters. Second, we adapt a differentiable Gaussian Splatting framework to the counting task by parameterizing each primitive with geometric parameters and a scalar density mass. This formulation allows the network to be trained end-to-end via spatial matching of differentiably rendered density maps, naturally providing both local density supervision and global count optimization. Extensive evaluations on four standard benchmarks show GDSNet consistently outperforms the state of the art.