SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hao, Yeh Keng, Wei, Hsu Tzu, Min, Sun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909877729755136
author Hao, Yeh Keng
Wei, Hsu Tzu
Min, Sun
author_facet Hao, Yeh Keng
Wei, Hsu Tzu
Min, Sun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
Hao, Yeh Keng
Wei, Hsu Tzu
Min, Sun
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.16396