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

arXiv: https://arxiv.org/abs/2303.12790 · HTML: https://mlsanity.com/paper/2303.12790/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 40 of its 64 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 40)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection](https://mlsanity.com/paper/1906.07538/) (2019)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Localization in the Crowd with Topological Constraints](https://mlsanity.com/paper/2012.12482/) (2020)
- [Point in, Box out: Beyond Counting Persons in Crowds](https://mlsanity.com/paper/1904.01333/) (2019)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [DiffusionInst: Diffusion Model for Instance Segmentation](https://mlsanity.com/paper/2212.02773/) (2022)
- [From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer](https://mlsanity.com/paper/1908.06473/) (2019)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [NAS-Count: Counting-by-Density with Neural Architecture Search](https://mlsanity.com/paper/2003.00217/) (2020)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)

## Built on by (most cited first, 20 of 20)

- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Diffusion-based Data Augmentation for Object Counting Problems](https://mlsanity.com/paper/2401.13992/) (2024)
- [Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection](https://mlsanity.com/paper/2504.21614/) (2025)
- [Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting](https://mlsanity.com/paper/2602.11024/) (2026)
- [Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting](https://mlsanity.com/paper/2602.12774/) (2026)
- [Enhancing Zero-shot Counting via Language-guided Exemplar Learning](https://mlsanity.com/paper/2402.05394/) (2024)
- [Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding](https://mlsanity.com/paper/2503.08152/) (2025)
- [Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization](https://mlsanity.com/paper/2503.12441/) (2025)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [CoDi -- an exemplar-conditioned diffusion model for low-shot counting](https://mlsanity.com/paper/2512.20153/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)
- [ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimation](https://mlsanity.com/paper/2501.01877/) (2025)
- [DiffMOD: Progressive Diffusion Point Denoising for Moving Object Detection in Remote Sensing](https://mlsanity.com/paper/2504.10278/) (2025)
- [Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection](https://mlsanity.com/paper/2509.10779/) (2025)
- [FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training](https://mlsanity.com/paper/2602.01540/) (2026)
- [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026)
- [Pix2Pix-Hybrid: Structure-Guided Conditional Synthesis of Hajj Crowd Images with Multi-Channel Conditioning and Weak Attribute Supervision](https://mlsanity.com/paper/2606.14297/) (2026)
- [Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting](https://mlsanity.com/paper/2606.18566/) (2026)
- [ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation](https://mlsanity.com/paper/2606.23835/) (2026)
- [CrowdCue: Specialist-Cue Conditioning for Vision-Language Crowd Counting](https://mlsanity.com/paper/2609.23012/) (2026)

## Abstract (arXiv)

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.