Text-to-Any-Skeleton Motion Generation Without Retargeting
Text-to-motion generation on arbitrary skeletons, no retargeting needed.
qingyuan-liu
•
•
1 min read
Realistic Full-Body Motion Generation from Sparse Tracking with State Space Model
State-space model for realistic motion generation from sparse trackers.
kun-dong
Motion Reconstruction via Human Anatomy Diffusion from Sparse Tracking
Anatomy-aware diffusion model for motion reconstruction from sparse trackers.
FlexControl: Flexible and Efficient Full-Body Controllable Text-to-Motion Generation
Flexible and efficient text-to-motion generation with full-body control.
qingyuan-liu
Skeleton Cluster Tracking for Robust Multi-view Multi-person 3D Human Pose Estimation
Robust multi-view multi-person 3D pose estimation via skeleton clustering.
From Methods to Applications: A Review of Deep 3D Human Motion Capture
A comprehensive survey of deep-learning-based 3D human motion capture.
FoodSAM: Any Food Segmentation
A SAM-based framework for high-quality food image segmentation.
xing-lan
Multi-view 3D Smooth Human Pose Estimation based on Heatmap Filtering and Spatio-temporal Information
Smooth multi-view 3D pose estimation via heatmap filtering + spatio-temporal info.