# Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection

arXiv: https://arxiv.org/abs/2405.15939 · HTML: https://mlsanity.com/paper/2405.15939/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 70 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields](https://mlsanity.com/paper/2207.13807/) (2022)
- [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023)
- [Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images](https://mlsanity.com/paper/1908.00439/) (2019)
- [GFPose: Learning 3D Human Pose Prior with Gradient Fields](https://mlsanity.com/paper/2212.08641/) (2022)
- [Neural Texture Extraction and Distribution for Controllable Person Image Synthesis](https://mlsanity.com/paper/2204.06160/) (2022)
- [SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling](https://mlsanity.com/paper/2303.17368/) (2023)
- [Pose Invariant Embedding for Deep Person Re-identification](https://mlsanity.com/paper/1701.07732/) (2017)
- [Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection](https://mlsanity.com/paper/1706.03038/) (2017)
- [DPE: Disentanglement of Pose and Expression for General Video Portrait Editing](https://mlsanity.com/paper/2301.06281/) (2023)

## Built on by (most cited first, 5 of 5)

- [Exploring the Potential of Synthetic Data to Replace Real Data](https://mlsanity.com/paper/2408.14559/) (2024)
- [SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception](https://mlsanity.com/paper/2408.11814/) (2024)
- [PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data](https://mlsanity.com/paper/2503.13025/) (2025)
- [UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting](https://mlsanity.com/paper/2504.02158/) (2025)
- [AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs](https://mlsanity.com/paper/2503.22884/) (2025)

## Abstract (arXiv)

Synthetic data generation has emerged as a promising solution to the data scarcity issue in aerial-view human detection. However, creating datasets that accurately reflect varying real-world human appearances, particularly diverse poses, remains challenging and labor-intensive. To address this, we propose SynPoseDiv, a novel framework that diversifies human poses within existing synthetic datasets. SynPoseDiv tackles two key challenges: generating realistic, diverse 3D human poses using a diffusion-based pose generator, and producing images of virtual characters in novel poses through a source-to-target image translator. The framework incrementally transitions characters into new poses using optimized pose sequences identified via Dijkstra's algorithm. Experiments demonstrate that SynPoseDiv significantly improves detection accuracy across multiple aerial-view human detection benchmarks, especially in low-shot scenarios, and remains effective regardless of the training approach or dataset size.