Human Pose Estimation (HPE) is increasingly utilized across various sectors, from healthcare to Industry 5.0. To address the inherent inaccuracies in CNN-based HPE systems, filtering models are commonly employed to refine and improve inference results. However, state-of-the-art filtering models often require substantial computational resources, lim- iting their applicability in resource-constrained environments. To overcome this limitation, we propose a real-time filtering approach based on denoising diffusion models (DM) specifically optimized for edge devices. Through a micro-benchmarking process, we analyze the DM adaptability to different types and levels of noise and determine the optimal setup for specific application scenarios. We present a real-time filter that takes advantage of the DM setup with two configurations to address different application scenarios. Using a widespread edge device, we evaluate the model’s effectiveness in handling both synthetic and real noise generated by state-of-the-art HPE systems. The results demonstrate a significant improvement in real-time filtering performance with minimal computational overhead. The code is available on github.com/PARCO-LAB/LUT-DM- filters.

A Real-time Filter for Human Pose Estimation based on Denoising Diffusion Models for Edge Devices

Chiara Bozzini;Michele Boldo;Enrico Martini;Nicola Bombieri
2024-01-01

Abstract

Human Pose Estimation (HPE) is increasingly utilized across various sectors, from healthcare to Industry 5.0. To address the inherent inaccuracies in CNN-based HPE systems, filtering models are commonly employed to refine and improve inference results. However, state-of-the-art filtering models often require substantial computational resources, lim- iting their applicability in resource-constrained environments. To overcome this limitation, we propose a real-time filtering approach based on denoising diffusion models (DM) specifically optimized for edge devices. Through a micro-benchmarking process, we analyze the DM adaptability to different types and levels of noise and determine the optimal setup for specific application scenarios. We present a real-time filter that takes advantage of the DM setup with two configurations to address different application scenarios. Using a widespread edge device, we evaluate the model’s effectiveness in handling both synthetic and real noise generated by state-of-the-art HPE systems. The results demonstrate a significant improvement in real-time filtering performance with minimal computational overhead. The code is available on github.com/PARCO-LAB/LUT-DM- filters.
2024
Denoising Diffusion Models
Human pose estimation
Filtering
Edge Devices
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1135766
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact