ScaleHP: Estimating Hand Pose in Metric Space

• URL: http://arxiv.org/abs/2606.25619v1
• Date: Wed, 24 Jun 2026 09:26:24 GMT
• Title: ScaleHP: Estimating Hand Pose in Metric Space
• Abstract summary: metric-space hand pose estimation is essential for immersive human-computer interaction and robotics.<n>In this work, we observe that the intrinsic proportional relationships among human hand bones encode stable anthropometric priors.<n>We present ScaleHP, an end-to-end one-stage hand pose estimation framework.
• Score: 47.87594046010537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate metric-space hand pose estimation (HPE) is essential for immersive human-computer interaction and robotics. However, most existing methods predict poses in a root-relative coordinate system and cannot estimate the hand in absolute metric scale. In this work, we observe that the intrinsic proportional relationships among human hand bones encode stable anthropometric priors that implicitly correlate with the overall metric size of the hand. Leveraging this insight, we present ScaleHP, an end-to-end one-stage hand pose estimation framework that bypasses fragile extrinsic depth modules to recover the hand in metric space. ScaleHP employs a transformer-based decoder with a novel scale token to fuse multi-scale morphological and appearance features. By solving for metric coordinates through a perspective-constrained least-squares approach, we achieve high-precision pose estimation in the camera coordinate system. ScaleHP delivers state-of-the-art performance, including 35.8 CS-MPJPE on FreiHand and 4.6/5.9 PA-MPJPE on DexYCB and HO3Dv3. These results demonstrate that internal biological constraints significantly reduce relative geometry and absolute metric errors, offering a robust solution for generalized, real-world hand tracking.

Related papers

• HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation [60.2305990057581]
  3D hand pose estimation is crucial for many human-computer interaction applications such as augmented reality.<n>HandMCM is a novel method based on the powerful state space model (Mamba)
  arXiv  Detail & Related papers  (2026-02-02T03:25:43Z)
• Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation [29.05126213133674]
  We introduce aleatoric uncertainty modeling into the 3D hand pose estimation framework.<n>We propose a novel parameterization that leverages a single linear layer to capture intrinsic correlations among hand joints.<n>Our experiments demonstrate that our parameterization for uncertainty modeling outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-09-01T08:31:01Z)
• 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)
• X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention [63.64944381130373]
  In particular, predominant pose estimation methods estimate human joints by 2D single-peak heatmaps. We introduce a lightweight and powerful alternative, Spatially Unidimensional Self-Attention (SUSA), to the pointwise (1x1) convolution. Our SUSA reduces the computational complexity of the pointwise (1x1) convolution by 96% without sacrificing accuracy.
  arXiv  Detail & Related papers  (2023-10-12T05:33:25Z)
• Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameters [9.477719717840683]
  We propose an efficient variation of the previously proposed image-to-lixel approach to efficiently estimate hand meshes from the images. We introduce an inverted kinematic(IK) network to translate the estimated hand mesh to a biomechanically feasible set of joint rotation parameters. Our Lite I2L Mesh Net achieves state-of-the-art joint and mesh estimation accuracy with less than $13%$ of the total computational complexity.
  arXiv  Detail & Related papers  (2023-03-26T22:24:12Z)
• Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation [51.00725889172323]
  We propose a Pose-Oriented Transformer (POT) with uncertainty guided refinement for 3D human pose estimation. We first develop novel pose-oriented self-attention mechanism and distance-related position embedding for POT to explicitly exploit the human skeleton topology. We present an Uncertainty-Guided Refinement Network (UGRN) to refine pose predictions from POT, especially for the difficult joints.
  arXiv  Detail & Related papers  (2023-02-15T00:22:02Z)
• Back to MLP: A Simple Baseline for Human Motion Prediction [59.18776744541904]
  This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. We show that the performance of these approaches can be surpassed by a light-weight and purely architectural architecture with only 0.14M parameters. An exhaustive evaluation on Human3.6M, AMASS and 3DPW datasets shows that our method, which we dub siMLPe, consistently outperforms all other approaches.
  arXiv  Detail & Related papers  (2022-07-04T16:35:58Z)
• HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty [2.064612766965483]
  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.
  arXiv  Detail & Related papers  (2021-11-02T08:55:45Z)
• Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction [137.28465645405655]
  HANDS'19 is a challenge to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set.
  arXiv  Detail & Related papers  (2020-03-30T19:28:13Z)
• Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation [16.463390330757132]
  We propose metric-scale truncation-robust volumetric heatmaps, whose dimensions are defined in metric 3D space near the subject. We train a fully-convolutional network to estimate such heatmaps from monocular RGB in an end-to-end manner. As our method is simple and fast, it can become a useful component for real-time top-down multi-person pose estimation systems.
  arXiv  Detail & Related papers  (2020-03-05T22:38:13Z)

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.