arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02598cs.CV
收藏

Synthetic-Child: 一种基于AIGC的合成数据管道用于隐私保护的儿童姿态估计

Synthetic-Child: An AIGC-Based Synthetic Data Pipeline for Privacy-Preserving Child Posture Estimation

Independent Researcher(独立研究者)

Taowen Zeng

AI总结:

Synthetic-Child通过AIGC生成合成数据,实现隐私保护下的儿童姿态估计,提升准确性和部署效率。

摘要:

准确的儿童姿态估计对于AI驱动的学习伴侣设备至关重要,但收集大规模标注的儿童数据既昂贵又因隐私问题而具有伦理上的不可接受性。我们提出了Synthetic-Child,一种基于AIGC的合成数据管道,能够生成逼真的儿童姿态训练图像,并带有地面真实值投影的关键点注释,无需任何真实的儿童照片。该管道包含四个阶段:(1)一个可编程的3D儿童身体模型(SMPL-X)在Blender中生成多样化的桌学习姿势,具有IK约束的解剖学合理性,并自动导出COCO格式的地面真实值;(2)一个定制的PoseInjectorNode将3D衍生的骨骼馈入一个双控制网(姿态+深度),基于FLUX-1 Dev进行条件合成,生成12,000张逼真的图像,覆盖10种姿态类别,具有低注释漂移;(3)基于ViTPose的置信度过滤和针对性增强去除生成失败并提高鲁棒性;(4)RTMPose-M(13.6M参数)在合成数据上进行微调,并与几何特征工程和轻量级MLP结合用于姿态分类,然后量化为INT8以实现实时边缘部署。在真实儿童测试集(n~300)上,FP16模型达到71.2 AP——在相同模型容量下,比COCO预训练成人数据基线提高了12.5 AP。在INT8量化后,模型保持70.4 AP,能够在0.8 TOPS的Rockchip RK3568 NPU上以22 FPS运行。在单个受试者受控比较中,与商业姿态校正器相比,我们的系统在大多数测试类别中实现了显著更高的识别率,并且平均响应时间快约1.8倍。这些结果表明,精心设计的AIGC管道可以显著减少对真实儿童图像的依赖,同时实现可部署的准确性,具有应用于其他隐私敏感领域的潜力。

英文摘要:

Accurate child posture estimation is critical for AI-powered study companion devices, yet collecting large-scale annotated datasets of children is both expensive and ethically prohibitive due to privacy concerns. We present Synthetic-Child, an AIGC-based synthetic data pipeline that produces photorealistic child posture training images with ground-truth-projected keypoint annotations, requiring zero real child photographs. The pipeline comprises four stages: (1) a programmable 3D child body model (SMPL-X) in Blender generates diverse desk-study poses with IK-constrained anatomical plausibility and automatic COCO-format ground-truth export; (2) a custom PoseInjectorNode feeds 3D-derived skeletons into a dual ControlNet (pose + depth) conditioned on FLUX-1 Dev, synthesizing 12,000 photorealistic images across 10 posture categories with low annotation drift; (3) ViTPose-based confidence filtering and targeted augmentation remove generation failures and improve robustness; (4) RTMPose-M (13.6M params) is fine-tuned on the synthetic data and paired with geometric feature engineering and a lightweight MLP for posture classification, then quantized to INT8 for real-time edge deployment. On a real-child test set (n~300), the FP16 model achieves 71.2 AP -- a +12.5 AP improvement over the COCO-pretrained adult-data baseline at identical model capacity. After INT8 quantization the model retains 70.4 AP while running at 22 FPS on a 0.8-TOPS Rockchip RK3568 NPU. In a single-subject controlled comparison with a commercial posture corrector, our system achieves substantially higher recognition rates across most tested categories and responds ~1.8x faster on average. These results demonstrate that carefully designed AIGC pipelines can substantially reduce dependence on real child imagery while achieving deployment-ready accuracy, with potential applications to other privacy-sensitive domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑