HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty

• URL: http://arxiv.org/abs/2111.01440v2
• Date: Wed, 3 Nov 2021 11:41:42 GMT
• Title: HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty
• Authors: Giorgio Cantarini, Federico Figari Tomenotti, Nicoletta Noceti, Francesca Odone
• Abstract summary: We introduce a novel method to estimate the head pose of people in single images starting from a small set of head keypoints. Our model is simple to implement and more efficient with respect to the state of the art.
• Score: 2.064612766965483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we introduce a novel method to estimate the head pose of people in single images starting from a small set of head keypoints. To this purpose, we propose a regression model that exploits keypoints computed automatically by 2D pose estimation algorithms and outputs the head pose represented by yaw, pitch, and roll. Our model is simple to implement and more efficient with respect to the state of the art -- faster in inference and smaller in terms of memory occupancy -- with comparable accuracy. Our method also provides a measure of the heteroscedastic uncertainties associated with the three angles, through an appropriately designed loss function; we show there is a correlation between error and uncertainty values, thus this extra source of information may be used in subsequent computational steps. As an example application, we address social interaction analysis in images: we propose an algorithm for a quantitative estimation of the level of interaction between people, starting from their head poses and reasoning on their mutual positions. The code is available at https://github.com/cantarinigiorgio/HHP-Net.

Related papers

• DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses [59.51874686414509]
  Current approaches approximate the continuous pose representation with a large number of discrete pose hypotheses. We present a Deep Voxel Matching Network (DVMNet) that eliminates the need for pose hypotheses and computes the relative object pose in a single pass. Our method delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-20T15:41:32Z)
• VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space [43.368963897752664]
  This work introduces a novel paradigm to address the Human Pose and Shape Estimation problem. Instead of predicting body model parameters, we focus on predicting the proposed discrete latent representation. The proposed model, VQ-HPS, predicts the discrete latent representation of the mesh.
  arXiv  Detail & Related papers  (2023-12-13T17:08:38Z)
• Match and Locate: low-frequency monocular odometry based on deep feature matching [0.65268245109828]
  We introduce a novel approach for the robotic odometry which only requires a single camera. The approach is based on matching image features between the consecutive frames of the video stream using deep feature matching models. We evaluate the performance of the approach in the AISG-SLA Visual Localisation Challenge and find that while being computationally efficient and easy to implement our method shows competitive results.
  arXiv  Detail & Related papers  (2023-11-16T17:32:58Z)
• Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence [1.7188280334580193]
  We introduce an ellipsoid-specific theoretical framework and demonstrate its beneficial properties in the context of pose estimation. We show that the proposed formalism enables to reduce the pose estimation problem to a position or orientation-only estimation problem.
  arXiv  Detail & Related papers  (2022-08-26T09:15:20Z)
• Poseur: Direct Human Pose Regression with Transformers [119.79232258661995]
  We propose a direct, regression-based approach to 2D human pose estimation from single images. Our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
  arXiv  Detail & Related papers  (2022-01-19T04:31:57Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)
• SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation [81.03485688525133]
  We propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE) Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network.
  arXiv  Detail & Related papers  (2021-04-06T13:12:51Z)
• Fast Uncertainty Quantification for Deep Object Pose Estimation [91.09217713805337]
  Deep learning-based object pose estimators are often unreliable and overconfident. In this work, we propose a simple, efficient, and plug-and-play UQ method for 6-DoF object pose estimation.
  arXiv  Detail & Related papers  (2020-11-16T06:51:55Z)
• Deep Convolutional Neural Network-based Bernoulli Heatmap for Head Pose Estimation [11.676928225717337]
  This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image. Our method can achieve the positioning of the head area while estimating the angles of the head. A deep convolutional neural network (CNN) structure with multiscale representations is adopted to maintain high-resolution information.
  arXiv  Detail & Related papers  (2020-05-24T15:36:29Z)
• HP2IFS: Head Pose estimation exploiting Partitioned Iterated Function Systems [18.402636415604373]
  Estimating the actual head orientation from 2D images is a well known problem. We use fractal coding theory and Partitioned Iterated Systems to extract the fractal code from the input head image. The proposed PIFS based head pose estimation method provides accurate yaw/pitch/roll angular values.
  arXiv  Detail & Related papers  (2020-03-25T17:56:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.