POSEidon: Face-from-Depth for Driver Pose Estimation
Fast and accurate upper-body and head pose estimation is a key task for automatic monitoring of driver attention, a challenging context characterized by severe illumination changes, occlusions and extreme poses. In this work, we present a new deep learning framework for head localization and pose estimation on depth images. The core of the proposal is a regression neural network, called POSEidon, which is composed of three independent convolutional nets followed by a fusion layer, specially conceived for understanding the pose by depth. In addition, to recover the intrinsic value of face appearance for understanding head position and orientation, we propose a new Face-from-Depth approach for learning image faces from depth. Results in face reconstruction are qualitatively impressive. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Results show that our method overcomes all recent state-of-art works, running in real time at more than 30 frames per second.
Code (0)
등록된 구현이 없습니다.
Tasks
Face ReconstructionHead Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
Face-from-Depth for Head Pose Estimation on Depth Images
Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a comple…
Head DetectionHead Pose EstimationPose EstimationPoseidon: Efficient Foundation Models for PDEs
We introduce Poseidon, a foundation model for learning the solution operators of PDEs. It is based on a multiscale operator transformer, with time-conditioned layer norms that enable continuous-in-time evaluations. A nov…
Operator learningPOSEIDON: Physics-Optimized Seismic Energy Inference and Detection Operating Network
Earthquake prediction and seismic hazard assessment remain fundamental challenges in geophysics, with existing machine learning approaches often operating as black boxes that ignore established physical laws. We introduc…
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion
Human pose estimation, a vital task in computer vision, involves detecting and localising human joints in images and videos. While single-frame pose estimation has seen significant progress, it often fails to capture the…
2D Human Pose EstimationComputational EfficiencyMulti-Person Pose EstimationPose EstimationPoseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters
Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial p…
GPUimage-classificationImage Classification