3D pose estimation
PulseAugur coverage of 3D pose estimation — every cluster mentioning 3D pose estimation across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New WiSPER framework enhances multi-person 3D pose estimation using WiFi CSI
Researchers have developed WiSPER, a novel two-stage framework for multi-person 3D pose estimation using WiFi channel state information (CSI). The system employs pose-aware predictive pretraining with conditional residu…
-
New EGGroW algorithms unlock efficient geodesic Gromov-Wasserstein distances for 3D modeling
Researchers have developed EGGroW, a novel class of algorithms designed to efficiently compute geodesic Gromov-Wasserstein distances. These distances are crucial for comparing probability distributions across different …
-
New distillation method improves infant 3D pose estimation
Researchers have developed a method to improve 3D human pose estimation for infants using cross-model distillation. By training the SAM 3D Body model on unannotated infant video, they were able to transfer knowledge fro…
-
New mmWave-language model mmMind bridges gap between radar sensing and LLMs
Researchers have developed mmMind, a novel radar-language model designed to enable large language models to understand human behavior in physical spaces. This model utilizes synchronized 3D pose data during training as …
-
VARPose enhances 2D pose estimation with autoregressive modeling
Researchers have introduced VARPose, a novel method for enhancing 2D human pose estimation by adaptively densifying sparse poses. This technique utilizes Visual Autoregressive Modeling (VAR) and a Granularity-agnostic P…
-
AI pipeline measures patient movement from smartphone video
Researchers have developed Quantitative Movement Testing (QMT), a computer vision pipeline that extracts 3D kinematic biomarkers from standard smartphone videos. This method uses deep learning-based 3D pose estimation t…
-
Researchers develop new method for analyzing whole-body coordination in sports motion
Researchers have developed a novel method called Complex Hilbert Principal Component Analysis (CHPCA) to analyze whole-body coordination in sports motion using markerless 3D pose estimation data. This technique segments…