SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization

Qi Zhang; Daijie Chen; Yunfei Gong; Hui Huang

cs.CVMar 25, 2026

SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization

Authors: Qi Zhang, Daijie Chen, Yunfei Gong, Hui Huang

Organizations: Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China.

Abstract

Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods impractical, as small datasets are easily overfit by these methods. To avoid these issues, 3DROM proposes a data augmentation method. Instead, in this paper, we propose a large synthetic benchmark, SynMVCrowd, for more practical evaluation and comparison of multi-view crowd counting and localization tasks. The SynMVCrowd benchmark consists of 50 synthetic scenes with a large number of multi-view frames and camera views and a much larger crowd number (up to 1000), which is more suitable for large-scene multi-view crowd vision tasks. Besides, we propose strong multi-view crowd localization and counting baselines that outperform all comparison methods on the new SynMVCrowd benchmark. Moreover, we prove that better domain transferring multi-view and single-image counting performance could be achieved with the aid of the benchmark on novel new real scenes. As a result, the proposed benchmark could advance the research for multi-view and single-image crowd counting and localization to more practical applications. The codes and datasets are here: https://github.com/zqyq/SynMVCrowd.

Figures & tables

Figure 1: The visualization of the proposed SynMVCrowd dataset: the type of scene, time stamps, and the weather condition.

Figure 2: The whole process of the multi-view crowd image generation, including scene setup, character setup, and the scene synthesis.

Figure 3: The two pie charts respectively illustrate the distribution of time stamps and weather conditions in SynMVCrowd. On the right side, each label denotes a time of 24 hours.

Figure 4: The action catalog of SynMVCrowd, consisting of various human poses in daily life.

Figure 5: The frame numbers of crowd count distributions of SynMVCrowd.

Figure 6: The scene examples of SynMVCrowd. The orange box contains a perspective from the training set. The green and blue boxes contain a perspective from the validation and test sets.

Dataset	Type	Scenes	Size	Cameras	Frames	Average	Counting Statistics
Dataset	Type	Scenes	Size	Cameras	Frames	Resolution	Total	Min	Avg	Max
PETS2009 Ferryman and Shahrokni (2009)	Real	1	-	3	1,899	576 $\times$ 768	-	20	-	40
DukeMTMC Ristani et al. (2016)	Real	1	-	4	989	1080 $\times$ 1920	-	10	-	30
Wildtrack Chavdarova et al. (2018)	Real	1	12 $\times$ 36	7	400	1080 $\times$ 1920	-	-	20	-
MultiviewX Hou et al. (2020)	Syn	1	16 $\times$ 25	6	400	1080 $\times$ 1920	-	-	40	-
CityStreet Zhang and Chan (2019)	Real	1	58 $\times$ 72	3	500	1520 $\times$ 2704	64K	70	128	150

Table 1: The statistical comparison of the proposed SynMVCrowd and six existing multi-view crowd datasets.

Figure 7: The dataset samples of scale variations.

Dataset	Type	Year	Average	Number	Counting Statistics
Dataset	Type	Year	Resolution	of Images	Total	Min	Avg	Max
USCD Chan et al. (2008)	Real	2008	158 $\times$ 238	2,000	50K	11	25	46
Mall Chen et al. (2012)	Real	2012	240 $\times$ 320	2,000	62K	13	31	53
UCF_CC_50 Idrees et al. (2013)	Real	2013	2101 $\times$ 2888	50	64K	94	1,280	4,543
WorldExpo’10 Zhang et al. (2015)	Real	2015	576 $\times$ 720	3,980	200K	1	50	253
ShanghaiTech Part A Zhang et al. (2016)	Real	2016	589 $\times$ 868	482	242K	33	501	3,139

Table 2: The statistic comparison of the proposed SynMVCrowd and nine existing single-image crowd datasets.

Figure 8: The pipeline of multi-view localization and counting baseline model: single-image feature extraction, spatial feature selection, multi-view feature projection and fusion, and multi-view decoding with MSE or Optimal Transport (OT) loss.

Figure 9: The visualization results of multi-view crowd localization: the first row is the camera view input, and the second row is the corresponding ground truth (GT) and prediction results.

Method	MODA $\uparrow$	MODP $\uparrow$	Precision $\uparrow$	Recall $\uparrow$	F1_score $\uparrow$
MVDet Hou et al. (2020)	27.0	52.2	72.2	43.9	54.6
SHOT Song et al. (2021)	32.5	52.6	74.5	49.3	59.3
MVDeTr Hou and Zheng (2021)	35.6	69.7	95.4	37.4	53.7
3DROM Qiu et al. (2022)	24.2	59.2	86.1	28.8	43.2
SVCW Zhang et al. (2024)	35.8	55.6	75.8	51.7	61.4
MVOT Zhang et al. (2024)	45.5	66.3	83.4	56.9	67.6

Table 3: The results of multi-view crowd localization methods on the SynMVCrowd dataset. Our baseline method, Baseline (OT) outperforms all comparisons.

Dataset	Wildtrack					MultiviewX
Method	MA.	MP.	P.	R.	F1.	MA.	MP.	P.	R.	F1.
RCNN Xu et al. (2016)	11.3	18.4	68	43	52.7	18.7	46.4	63.5	43.9	51.9
POM-CNN Fleuret et al. (2007)	23.2	30.5	75	55	63.5	-	-	-	-	-
DeepMCD Chavdarova and Fleuret (2017)	67.8	64.2	85	82	83.5	70.0	73.0	85.7	83.3	84.5
DeepOcc. Baqué et al. (2017)	74.1	53.8	95	80	86.9	75.2	54.7	97.8	80.2	88.1
Volumetric Iskakov et al. (2019)	88.6	73.8	95.3	93.2	94.2	84.2	80.3	97.5	86.4	91.6

Table 4: Comparison of the multi-view people detection performance on Wildtrack and MultiviewX using 5 metrics. All comparison methods train and test on Wildtrack or MultiviewX (single scene), while ours are trained on SynMVCrowd and finetuned on Wildtrack or MultiviewX or with the domain adaptation technique.

Figure 10: The visualization results of multi-view crowd counting: the first row is the camera view input, and the second is the corresponding ground truth (GT) and prediction results.

Method	MAE $\downarrow$	NAE $\downarrow$	MSE $\downarrow$
MVMS Zhang and Chan (2020)	81.51	0.173	102.74
MVMSR Zhang and Chan (2020)	70.60	0.143	93.26
CVCS backbone Zhang et al. (2021)	72.50	0.154	93.99
CVCS Zhang et al. (2021)	67.74	0.139	89.31
3DCounting Zhang and Chan (2020)	74.63	0.171	101.30
CountFormer Mo et al. (2024)	56.30	0.117	79.30

Table 5: The results of multi-view crowd counting methods on the SynMVCrowd dataset.

Model	MAE $\downarrow$	MSE $\downarrow$	NAE $\downarrow$	MODA $\uparrow$	MODP $\uparrow$	Precision $\uparrow$	Recall $\uparrow$	F1_score $\uparrow$
VGG19	59.04	83.00	0.155	43.8	69.6	88.4	51.6	65.0
ResNet18	50.20	68.19	0.104	49.6	70.2	88.6	57.0	69.4
Transformer	66.23	92.84	0.211	39.5	62.1	80.1	48.3	60.3

Table 6: The multi-view counting and localization performance comparison of using different feature extraction backbones in the Baseline (OT) model, which is trained on the SynMVCrowd dataset with 5 views as input.

Models	test views	MAE $\downarrow$	MSE $\downarrow$	NAE $\downarrow$
CountFormer	3	47.71	65.24	0.151
	5	56.30	79.30	0.117
	7	71.47	95.95	0.158
	9	77.82	102.96	0.164
Baseline (OT)	3	57.97	69.00	0.137
	5	50.20	68.19	0.104

Table 7: Testing the baseline model on the multi-view counting task under different camera view numbers.

Loss	Module	MAE $\downarrow$	MSE $\downarrow$	NAE $\downarrow$	MODA $\uparrow$	MODP $\uparrow$	Precision $\uparrow$	Recall $\uparrow$	F1_score $\uparrow$
MSE	Without	74.33	97.52	0.236	31.9	74.8	94.1	34.0	49.9
MSE	With	68.79	92.04	0.158	34.6	74.5	92.9	37.4	53.4
OT	Without	52.94	78.21	0.105	46.7	69.7	87.9	54.1	67.0
OT	With	50.20	68.19	0.104	49.6	70.2	88.6	57.0	69.4

Table 8: Performance Comparison of baseline model with/without spatial feature selection module using MSE or OT loss.

Pitch	MAE $\downarrow$	MSE $\downarrow$	NAE $\downarrow$	MODA $\uparrow$	MODP $\uparrow$	Precision $\uparrow$	Recall $\uparrow$	F1_score $\uparrow$
$[-90,-60)$	48.19	67.00	0.100	46.0	64.9	85.0	55.9	67.4
$[-60,-30)$	49.62	68.29	0.105	45.6	67.8	84.8	55.6	67.2
$[-30,0]$	55.97	76.03	0.118	42.9	66.7	83.4	53.6	65.2

Table 9: The performance comparison of the different pitch ranges.

Methods	Parameters (MB)	FLOPs (G)	Memory (MB)
MVDet Hou et al. (2020)	30.10	910.44	114.85
SHOT Song et al. (2021)	19.14	1230.24	73.04
MVDeTr Hou and Zheng (2021)	12.78	148.30	48.78
3DROM Zhang and Chan (2020)	32.46	1012.36	123.86
SVCW Zhang et al. (2024)	25.71	3413.13	98.12
MVOT Zhang et al. (2024)	18.59	349.73	70.95

Table 10: Computation statistic comparison of different methods.

	Dataset	CityStreet			PETS2009
Training	Method	MAE $\downarrow$	NAE $\downarrow$	MSE $\downarrow$	MAE $\downarrow$	NAE $\downarrow$	MSE $\downarrow$
Single-scene	Dmap_wtd Ryan et al. (2014)	11.10	0.121	-	7.51	0.261	-
	Dect+ReID Zhang and Chan (2019)	27.60	0.385	-	9.41	0.289	-
	LateFusion Zhang and Chan (2019)	8.12	0.097	-	3.92	0.138	-
	EarlyFusion Zhang and Chan (2019)	8.10	0.096	-	5.43	0.199	-
	MVMS (FCN-7) Zhang and Chan (2019)	8.01	0.096	10.05	3.49	0.124	4.83

Table 11: The multi-view crowd counting domain adaptation (DA) results on the CityStreet dataset and the PETS2009 dataset.

Method	MAE $\downarrow$	MSE $\downarrow$	Precision $\uparrow$	Recall $\uparrow$	F1_score $\uparrow$
CSRNet Li et al. (2018)	21.84	36.58	50.77	69.59	58.71
DM-Count Wang et al. (2020)	20.88	34.72	65.53	67.31	66.41
NoisyCC Wan and Chan (2020)	26.19	43.23	33.65	48.28	39.66
P2PNet Song et al. (2021)	61.74	115.03	80.59	67.62	73.54
GLoss Wan et al. (2021)	21.37	40.36	79.37	70.63	74.75
CLTR Liang et al. (2022)	23.86	38.53	85.47	66.02	74.50

Table 12: The performance of single-image crowd counting and localization SOTA methods ( with code available ) on the SynMVCrowd dataset. We report all methods’ single-image counting and localization performance.

Method	Sparse (0-399)		Medium (400-699)		Congested (700-1000)
Method	MAE $\downarrow$	MSE $\downarrow$	MAE $\downarrow$	MSE $\downarrow$	MAE $\downarrow$	MSE $\downarrow$
CSRNet Li et al. (2018)	14.92	23.69	27.06	42.75	45.17	64.85
DMCount Wang et al. (2020)	18.23	29.76	25.00	41.00	35.34	56.58
NoisyCC Wan and Chan (2020)	20.45	31.01	29.78	43.77	47.61	68.95
P2PNet Song et al. (2021)	27.77	35.15	45.26	66.01	79.96	92.04
GLoss Wan et al. (2021)	17.68	27.26	26.49	42.33	37.74	57.37

Table 13: The results on detailed evaluation granularity. We divide the scenes into 3 types regarding crowd numbers: ‘Sparse (0-399)’, ‘Medium (400-699)’, and ‘Congested (700-1000)’, and evaluate methods accordingly.

Figure 11: The visualization results of single-image crowd counting and localization.

Figure 12: Architecture of the domain adaptation network for single-image crowd counting. The model takes synthetic (source) and real (target) images as input. Features are encoded and selected, then processed through two branches: 1) A decoder producing density maps, supervised by MSE loss against ground truth; 2) A domain predictor distinguishing source from target features using cross-entropy (CE) loss. This adversarial training aligns feature distributions across domains to improve generalization.

Single-image baseline
Single-image feature extractor
Layer	Feature Extractor
Layer	UpSampling
Single-image decoder
Layer	Filter
conv 1	$512\!\times\!256\!\times\!3\!\times\!3$ , relu

Table 14: The single-image baseline for domain adaptation. The single-image baseline includes a single-image feature extractor, a single-image decoder, and a discriminator. The Filter dimensions are input channels, output channels, and filter size (

w\!\times\!h

Training	Dataset	SHA		SHB
Training	Method	MAE $\downarrow$	MSE $\downarrow$	MAE $\downarrow$	MSE $\downarrow$
Single-scene	MCNN Zhang et al. (2016)	110.20	173.20	26.40	41.30
	CSRNet Li et al. (2018)	68.20	115.00	10.60	16.00
	DM-Count Wang et al. (2020)	59.70	95.70	7.40	11.80
	GLoss Wan et al. (2021)	61.30	95.40	7.30	11.70
	GauNet Cheng et al. (2022)	54.80	89.10	6.20	9.90

Table 15: The single-image crowd counting domain adaptation results on the ShanghaiTech A and B dataset.

Figure 13: The domain adaptation visualization results of single-image crowd counting on ShanghaiTech B and ShanghaiTech A.

Datasets	UCF-CC-50			MALL
Method	MAE $\downarrow$	NAE $\downarrow$	MSE $\downarrow$	MAE $\downarrow$	NAE $\downarrow$	MSE $\downarrow$
Crowd-CNN Zhang et al. (2015)	466.90	-	498.60	1.83	-	2.76
MCNN Zhang et al. (2016)	377.60	-	509.10	2.74	-	13.50
CSRNet Li et al. (2018)	266.10	-	397.50	-	-	-
DecideNet Liu et al. (2018)	361.80	-	493.50	1.53	-	1.89
IG-CNN Sam et al. (2018)	419.60	-	541.80	2.39	-	9.14

Table 16: The single-image crowd counting domain adaptation results on UCF-CC-50 and Mall datasets. Comparisons are all trained and tested on the same datasets, while ours is trained on SynMVCrowd and tested on UCF-CC-50 or Mall.

Crowd Counting

Crowd counting estimates how many people appear in images or video, supporting occupancy monitoring, safety planning, and crowd management.

See all 23 papers

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
Apr 21, 2026Qi Zhang, Jixuan Chen, Kaiyi Zhang +3Multi-Object Tracking
College of Computer Science and Software Engineering, Shenzhen University, China · Department of Computer Science, City University of Hong Kong, China
Multi-view Optimal Transport for Multi-view Crowd Localization and Tracking
Sep 3, 2024Kaiyi Zhang, Qi Zhang, Jixuan Chen +2Multi-Object Tracking Optimal Transport
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China · Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China · Department of Computer Science, City University of Hong Kong, HK SAR, China
A Benchmark for Semi-supervised Multi-modal Crowd Counting
Jun 2, 2026Haoliang Meng, Xiaopeng Hong, Yabin Wang +1Crowd Counting Semi-Supervised Learning
Harbin Institute of Technology · Pengcheng Laboratory

Apr 21, 2026J/K move · Enter open · S save

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes

Qi Zhang, Jixuan Chen, Kaiyi Zhang, Xinquan Yu+2

College of Computer Science and Software Engineering, Shenzhen University, China · Department of Computer Science, City University of Hong Kong, China

Multi-Object Tracking

Open paper AskPDF arXiv

Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene. Recent research works mainly rely on CNNs-based multi-view crowd tracking architectures, and most of them are evaluated and compared on relatively small datasets, such as Wildtrack and MultiviewX. Since these two datasets are collected in small scenes and only contain tens of frames in the evaluation stage, it is difficult for the current methods to be applied to real-world applications where scene size and occlusion are more complicated. In this paper, we propose a Transformer-based multi-view crowd tracking model, MVTrackTrans, which adopts interactions between camera views and the ground plane for enhanced multi-view tracking performance. Besides, for better evaluation, we collect and label two large real-world multi-view tracking datasets, MVCrowdTrack and CityTrack, which contain a much larger scene size over a longer time period. Compared with existing methods on the two large and new datasets, the proposed MVTrackTrans model achieves better performance, demonstrating the advantages of the model design in dealing with large scenes. We believe the proposed datasets and model will push the frontiers of the task to more practical scenarios, and the datasets and code are available at: https://github.com/zqyq/MVTrackTrans.

Abstract

Crowd Counting

Explore similar work

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes

Multi-view Optimal Transport for Multi-view Crowd Localization and Tracking

A Benchmark for Semi-supervised Multi-modal Crowd Counting