SPLite Hand：感知稀疏性的轻量级3D手部姿态估计
SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
AI总结：
针对AR/VR边缘设备部署深度学习模型的效率与性能平衡难题，提出SPLite Hand轻量3D手部姿态估计框架，结合稀疏卷积、SPLite解码器与量化感知训练，在Raspberry Pi 5上实现显著加速且准确率接近最优水平。
摘要：
随着AR/VR设备日益普及，深度学习模型在边缘设备上的部署已成为关键挑战。这类设备要求实时推理、低功耗及最小延迟，许多框架设计者都面临效率与性能的平衡难题。我们设计了一种采用编码器-解码器架构的轻量框架，并提出多项关键改进以同时提升效率与准确率。我们在ResNet-18骨干网络上应用稀疏卷积，利用手部姿态图像中固有的稀疏性，实现了42%的端到端效率提升。此外，我们提出了SPLite解码器，这种新架构在Raspberry Pi 5上将解码过程的帧率显著提升了3.1倍，同时保持了相当的准确率。为进一步优化性能，我们应用了量化感知训练，在保留准确率的同时减少了内存占用（在FreiHAND数据集上，PA-MPJPE仅从9.0 mm微增至9.1 mm）。总体而言，我们的系统在Raspberry Pi 5 CPU（BCM2712四核Arm A76处理器）上实现了2.98倍的速度提升。我们的方法还在复合基准数据集上进行了评估，结果表明其准确率与当前最优方法相当，同时计算效率得到显著提升。
英文摘要：
With the increasing ubiquity of AR/VR devices, the deployment of deep learning models on edge devices has become a critical challenge. These devices require real-time inference, low power consumption, and minimal latency. Many framework designers face the conundrum of balancing efficiency and performance. We design a light framework that adopts an encoder-decoder architecture and introduces several key contributions aimed at improving both efficiency and accuracy. We apply sparse convolution on a ResNet-18 backbone to exploit the inherent sparsity in hand pose images, achieving a 42% end-to-end efficiency improvement. Moreover, we propose our SPLite decoder. This new architecture significantly boosts the decoding process's frame rate by 3.1x on the Raspberry Pi 5, while maintaining accuracy on par. To further optimize performance, we apply quantization-aware training, reducing memory usage while preserving accuracy (PA-MPJPE increases only marginally from 9.0 mm to 9.1 mm on FreiHAND). Overall, our system achieves a 2.98x speed-up on a Raspberry Pi 5 CPU (BCM2712 quad-core Arm A76 processor). Our method is also evaluated on compound benchmark datasets, demonstrating comparable accuracy to state-of-the-art approaches while significantly enhancing computational efficiency.
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。
