# Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

arXiv: https://arxiv.org/abs/1804.02047 · HTML: https://mlsanity.com/paper/1804.02047/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2018.

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

- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey](https://mlsanity.com/paper/2307.04370/) (2023)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis](https://mlsanity.com/paper/2109.02081/) (2021)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [Region-guided CycleGANs for Stain Transfer in Whole Slide Images](https://mlsanity.com/paper/2208.12847/) (2022)
- [Feature Calibration Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/2212.05717/) (2022)
- [CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise](https://mlsanity.com/paper/2108.00478/) (2021)
- [Attention-based Adversarial Appearance Learning of Augmented Pedestrians](https://mlsanity.com/paper/2107.02673/) (2021)
- [ARHNet: Adaptive Region Harmonization for Lesion-aware Augmentation to Improve Segmentation Performance](https://mlsanity.com/paper/2307.01220/) (2023)
- [Synthetic Data and Hierarchical Object Detection in Overhead Imagery](https://mlsanity.com/paper/2102.00103/) (2021)
- [Application of image-to-image translation in improving pedestrian detection](https://mlsanity.com/paper/2209.03625/) (2022)
- [presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search](https://mlsanity.com/paper/2608.21543/) (2026)

## Abstract (arXiv)

State-of-the-art pedestrian detection models have achieved great success in many benchmarks. However, these models require lots of annotation information and the labeling process usually takes much time and efforts. In this paper, we propose a method to generate labeled pedestrian data and adapt them to support the training of pedestrian detectors. The proposed framework is built on the Generative Adversarial Network (GAN) with multiple discriminators, trying to synthesize realistic pedestrians and learn the background context simultaneously. To handle the pedestrians of different sizes, we adopt the Spatial Pyramid Pooling (SPP) layer in the discriminator. We conduct experiments on two benchmarks. The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details. To quantitatively evaluate our approach, we add the generated samples into training data of the baseline pedestrian detectors and show the synthetic images are able to improve the detectors' performance.