GHNeRF: Efficient Neural Radiance Fields for Learning Generalizable Human Features
GHNeRF can simultaneously learn neural radiance fields and generalizable human features, such as 2D/3D joint locations and dense poses, from sparse 2D images.
SDPose: Efficient Transformer-based Human Pose Estimation via Self-Distillation and Cyclic Forwarding
A novel self-distillation framework, SDPose, that leverages a Multi-Cycled Transformer (MCT) module to improve the performance of small transformer-based human pose estimation models without increasing computational cost.
Exploiting Diffusion Prior for Accurate Occluded Human Mesh Recovery
The core message of this paper is to introduce DPMesh, an innovative framework that fully exploits the rich knowledge about object structure and spatial interaction within a pre-trained diffusion model to achieve accurate occluded human mesh recovery in a single step.
Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for Accurate 3D Human Pose Estimation
The proposed Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer) effectively models both spatial and temporal correlations in 3D human pose estimation by incorporating prior knowledge on human body kinematics and joint motion trajectories.
Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors
新しい人間の姿勢推定手法は、慣性センサーを使用して動的なモーションダイナミクスを学習し、スパースな慣性センサーで人間の姿勢推定を向上させる。
