paper-with-me

홈 › Papers

BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation

2022-06-23 · Ivan Grishchenko, Valentin Bazarevsky, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, Richard Yee, Karthik Raveendran, Matsvei Zhdanovich, Matthias Grundmann, Cristian Sminchisescu

We present BlazePose GHUM Holistic, a lightweight neural network pipeline for 3D human body landmarks and pose estimation, specifically tailored to real-time on-device inference. BlazePose GHUM Holistic enables motion capture from a single RGB image including avatar control, fitness tracking and AR/VR effects. Our main contributions include i) a novel method for 3D ground truth data acquisition, ii) updated 3D body tracking with additional hand landmarks and iii) full body pose estimation from a monocular image.

📄 PDF Abstract BibTeX arXiv:2206.11678

Code (0)

등록된 구현이 없습니다.

Tasks

3D Human Pose EstimationPose Estimation

Similar Papers 제목 키워드 기반

BlazePose: On-device Real-time Body Pose tracking

2020-06-17 · Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu 외

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints…

2D Human Pose Estimation3D Human Pose Estimation3D Pose EstimationPose Estimation+3

Physics Informed Human Posture Estimation Based on 3D Landmarks from Monocular RGB-Videos

2025-12-07 · Tobias Leuthold, Michele Xiloyannis, Yves Zimmermann arxiv

Applications providing automated coaching for physical training are increasing in popularity, for example physical therapy. These applications rely on accurate and robust pose estimation using monocular video streams. St…

3D Pose EstimationPose Tracking

imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose

2021-08-24 · ICCV 2021 10 · Thiemo Alldieck, Hongyi Xu, Cristian Sminchisescu

We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function z…

Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction

2023-09-11 · Ivan Grishchenko, Geng Yan, Eduard Gabriel Bazavan, Andrei Zanfir 외

We present Blendshapes GHUM, an on-device ML pipeline that predicts 52 facial blendshape coefficients at 30+ FPS on modern mobile phones, from a single monocular RGB image and enables facial motion capture applications l…

Prediction

Semi-Supervised Object Detection for Sorghum Panicles in UAV Imagery

2023-05-16 · Enyu Cai, Jiaqi Guo, Changye Yang, Edward J. Delp

The sorghum panicle is an important trait related to grain yield and plant development. Detecting and counting sorghum panicles can provide significant information for plant phenotyping. Current deep-learning-based objec…

object-detectionObject DetectionPlant PhenotypingSemi-Supervised Object Detection