$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models
This work improves crowd analysis for applications like surveillance and public safety, but it is incremental as it builds on existing diffusion model techniques for a specific domain.
The paper tackles the problem of crowd counting by addressing background noise and density loss in density map estimation, proposing CrowdDiff, a method using conditional diffusion models to generate multiple density maps, which outperforms state-of-the-art methods on public benchmarks with significant improvements.
Crowd counting is a fundamental problem in crowd analysis which is typically accomplished by estimating a crowd density map and summing over the density values. However, this approach suffers from background noise accumulation and loss of density due to the use of broad Gaussian kernels to create the ground truth density maps. This issue can be overcome by narrowing the Gaussian kernel. However, existing approaches perform poorly when trained with ground truth density maps with broad kernels. To deal with this limitation, we propose using conditional diffusion models to predict density maps, as diffusion models show high fidelity to training data during generation. With that, we present $CrowdDiff$ that generates the crowd density map as a reverse diffusion process. Furthermore, as the intermediate time steps of the diffusion process are noisy, we incorporate a regression branch for direct crowd estimation only during training to improve the feature learning. In addition, owing to the stochastic nature of the diffusion model, we introduce producing multiple density maps to improve the counting performance contrary to the existing crowd counting pipelines. We conduct extensive experiments on publicly available datasets to validate the effectiveness of our method. $CrowdDiff$ outperforms existing state-of-the-art crowd counting methods on several public crowd analysis benchmarks with significant improvements.