mlsanityData to 7 Oct 2026

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

arXiv 2405.15939 ↗First posted 24 May 2024cs.CVcited by 5

Not on the map. Why?

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 50 of its 70 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

50 of 70 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  8. 2022Human Motion Diffusion Modelcited by 1,062
  9. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  11. 2019Object Detection in 20 Years: A Surveycited by 528
  12. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
38 more
  1. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  2. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  3. 2017Learning from Synthetic Humanscited by 358
  4. 2020Detection and Tracking Meet Drones Challengecited by 261
  5. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  6. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  7. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  8. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  9. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  10. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  11. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
  12. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67
  13. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  14. 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
  15. 2023SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modelingcited by 54
  16. 2017Pose Invariant Embedding for Deep Person Re-identificationcited by 47
  17. 2017Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detectioncited by 45
  18. 2023DPE: Disentanglement of Pose and Expression for General Video Portrait Editingcited by 45
  19. 2023Human Pose as Compositional Tokenscited by 45
  20. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  21. 2021Adversarial Parametric Pose Priorcited by 38
  22. 2016MoCap-guided Data Augmentation for 3D Pose Estimation in the Wildcited by 37
  23. 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
  24. 2019Mixture Dense Regression for Object Detection and Human Pose Estimationcited by 29
  25. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  26. 2021Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Datacited by 26
  27. 2023Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfercited by 25
  28. 20223D Segmentation of Humans in Point Clouds with Synthetic Datacited by 24
  29. 20223DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mappingcited by 17
  30. 2022PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimationcited by 14
  31. 2017ME R-CNN: Multi-Expert R-CNN for Object Detectioncited by 13
  32. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12
  33. 2019Human Synthesis and Scene Compositingcited by 11
  34. 2022Progressive Transformation Learning for Leveraging Virtual Images in Trainingcited by 10
  35. 2022Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadatacited by 8
  36. 2023Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-viewcited by 8
  37. 2022Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Datacited by 6
  38. 2022Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Texturescited by 6

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024Exploring the Potential of Synthetic Data to Replace Real Datacited by 3
  2. 2024SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perceptioncited by 1
  3. 2025PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Datacited by 1
  4. 2025UAVTwin: Neural Digital Twins for UAVs using Gaussian Splattingcited by 1
  5. 2025AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMscited by 0