# Pixel-wise Crowd Understanding via Synthetic Data

arXiv: https://arxiv.org/abs/2007.16032 · HTML: https://mlsanity.com/paper/2007.16032/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 23 of 23)

- [Polarized Self-Attention: Towards High-quality Pixel-wise Regression](https://mlsanity.com/paper/2107.00782/) (2021)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images](https://mlsanity.com/paper/2401.10530/) (2024)
- [Audio-visual Representation Learning for Anomaly Events Detection in Crowds](https://mlsanity.com/paper/2110.14862/) (2021)
- [Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network](https://mlsanity.com/paper/2107.12858/) (2021)
- [Bi-level Alignment for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2205.05844/) (2022)
- [Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting](https://mlsanity.com/paper/2505.21943/) (2025)
- [Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection](https://mlsanity.com/paper/2507.14807/) (2025)
- [Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification](https://mlsanity.com/paper/2109.05542/) (2021)
- [ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces](https://mlsanity.com/paper/2405.16016/) (2024)
- [Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator](https://mlsanity.com/paper/2103.15502/) (2021)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)
- [TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting](https://mlsanity.com/paper/2512.22203/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)
- [Multi-channel Deep Supervision for Crowd Counting](https://mlsanity.com/paper/2103.09553/) (2021)
- [Machines & Influence: An Information Systems Lens](https://mlsanity.com/paper/2111.13365/) (2021)
- [Training Robust Deep Physiological Measurement Models with Synthetic Video-based Data](https://mlsanity.com/paper/2311.05371/) (2023)
- [Improving Object Detection by Modifying Synthetic Data with Explainable AI](https://mlsanity.com/paper/2412.01477/) (2024)
- [Autonomous Crack Detection using Deep Learning on Synthetic Thermogram Datasets](https://mlsanity.com/paper/2412.16499/) (2024)

## Abstract (arXiv)

Crowd analysis via computer vision techniques is an important topic in the field of video surveillance, which has wide-spread applications including crowd monitoring, public safety, space design and so on. Pixel-wise crowd understanding is the most fundamental task in crowd analysis because of its finer results for video sequences or still images than other analysis tasks. Unfortunately, pixel-level understanding needs a large amount of labeled training data. Annotating them is an expensive work, which causes that current crowd datasets are small. As a result, most algorithms suffer from over-fitting to varying degrees. In this paper, take crowd counting and segmentation as examples from the pixel-wise crowd understanding, we attempt to remedy these problems from two aspects, namely data and methodology. Firstly, we develop a free data collector and labeler to generate synthetic and labeled crowd scenes in a computer game, Grand Theft Auto V. Then we use it to construct a large-scale, diverse synthetic crowd dataset, which is named as "GCC Dataset". Secondly, we propose two simple methods to improve the performance of crowd understanding via exploiting the synthetic data. To be specific, 1) supervised crowd understanding: pre-train a crowd analysis model on the synthetic data, then fine-tune it using the real data and labels, which makes the model perform better on the real world; 2) crowd understanding via domain adaptation: translate the synthetic data to photo-realistic images, then train the model on translated data and labels. As a result, the trained model works well in real crowd scenes.