25 November 2024 in Neural Networks
5 October 2024 in Neurocomputing
16 May 2025 in Neural Networks
18 March 2026 in IEEE Internet of Things Journal
Accurate 3-D hand pose estimation faces inherent challenges, including self-occlusions, joint similarities, and high degrees of freedom. Although most existing CNN-based or Transformer-based methods leverage global contexts, they often fail to capture fine-grained local details and robustly handle occluded joints. To address these limitations, we propose a novel Transformer framework for depth-based 3-D hand pose estimation, which incorporates two key designs: the bidirectional multiscale fusion (BMF) and learnable anchor guidance (LAG). First, we propose BMF that sequentially propagates features from different encoder levels in both top-down and bottom-up directions, followed by a final aggregation of all scale features. Such an intricate feature interaction eventually enables effective joint modeling of fine-grained local details (e.g., fingertip positions) and high-level semantic context information (e.g., palm orientation). Second, we introduce the learnable anchor query as prior guidance to dynamically guide the decoder to localize ambiguous joints better. The learnable anchors are derived from joint-specific attention maps under 3-D ground-truth supervision and then are concatenated with static grid anchors to form hybrid anchors, which effectively enable more precise 3-D hand pose estimation, especially for occlusions. To further demonstrate the practicality of our framework for IoT-oriented deployment, we conduct edge-device experiments to validate its deployment feasibility. Experiments on benchmark datasets (including NYU, ICVL, MSRA, and DexYCB) demonstrate the superiority of our method over previous state-of-the-art approaches.