# Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes

arXiv: https://arxiv.org/abs/2012.00946 · HTML: https://mlsanity.com/paper/2012.00946/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [Counting Stacked Objects](https://mlsanity.com/paper/2411.19149/) (2024)
- [Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting](https://mlsanity.com/paper/2405.19943/) (2024)
- [Deep Models for Multi-View 3D Object Recognition: A Review](https://mlsanity.com/paper/2404.15224/) (2024)
- [Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Models](https://mlsanity.com/paper/2512.16243/) (2025)
- [Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting](https://mlsanity.com/paper/2406.08814/) (2024)
- [Embodied Crowd Counting](https://mlsanity.com/paper/2503.08367/) (2025)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [Automated Counting of Stacked Objects in Industrial Inspection](https://mlsanity.com/paper/2603.15470/) (2026)
- [Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches](https://mlsanity.com/paper/2204.04653/) (2022)
- [Multi-View Crowd Counting With Self-Supervised Learning](https://mlsanity.com/paper/2509.21918/) (2025)
- [SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization](https://mlsanity.com/paper/2603.23956/) (2026)

## Abstract (arXiv)

Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces) because a single camera cannot capture the whole scene in adequate detail for counting, e.g., when the scene is too large to fit into the field-of-view of the camera, too long so that the resolution is too low on faraway crowds, or when there are too many large objects that occlude large portions of the crowd. Therefore, to solve the wide-area counting task requires multiple cameras with overlapping fields-of-view. In this paper, we propose a deep neural network framework for multi-view crowd counting, which fuses information from multiple camera views to predict a scene-level density map on the ground-plane of the 3D world. We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales. A rotation selection module further ensures consistent rotation alignment of the features. We test our 3 fusion models on 3 multi-view counting datasets, PETS2009, DukeMTMC, and a newly collected multi-view counting dataset containing a crowded street intersection. Our methods achieve state-of-the-art results compared to other multi-view counting baselines.