$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models

arXiv:2303.12790v3 Announce Type: replace
Abstract: 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 …

abstract analysis arxiv cs.cv diffusion diffusion models however hypothesis loss map noise type values