# Gaussian Density Splatting Network

arXiv: https://arxiv.org/abs/2610.10396 · HTML: https://mlsanity.com/paper/2610.10396/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling](https://mlsanity.com/paper/2503.06617/) (2025)
- [GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2407.18046/) (2024)
- [Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting](https://mlsanity.com/paper/2502.09039/) (2025)
- [Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution](https://mlsanity.com/paper/2501.06838/) (2025)
- [GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting](https://mlsanity.com/paper/2501.15619/) (2025)
- [GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation](https://mlsanity.com/paper/2509.01109/) (2025)
- [2D Gaussian Splatting with Semantic Alignment for Image Inpainting](https://mlsanity.com/paper/2509.01964/) (2025)

## Abstract (arXiv)

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, a control-point-based fitting mechanism is introduced to structure the prediction of Gaussian parameters. A set of control points is adaptively allocated to 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. The code is available at https://github.com/infinite0522/GDSNet-Gaussian-Density-Splatting-Network.