2024/05/24 by Yi‐Ting Shen, Hyungtae Lee, Shen, Yi-Ting +5
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrared Target Detection Methodologies #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2405.15939
openalex publication_date 2024/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
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.