HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

3D Human Pose Estimation On Total Capture

평가 지표

Average MPJPE (mm)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average MPJPE (mm)	Paper Title	Repository
IMUPVH	70	Total capture: 3D human pose estimation fusing video and inertial sensors	-
MTF-Transformer (M=0.4, T=7)	29.2	Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation	-
AdaFuse	19.2	AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
AutoEnc	35	Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling	-
LWCDR	27.5	Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation	-
PVH	107	Total capture: 3D human pose estimation fusing video and inertial sensors	-
Tri-CPM	99	Convolutional Pose Machines
DeepFuse-IMU	28.9	DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image	-
AdaDeepFuse	22.5	FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation	-
ROS node wrapping	112	3D Human Pose Estimation in RGBD Images for Robotic Task Learning
Fusion-RPSM	29.0	Cross View Fusion for 3D Human Pose Estimation
Single-RPSM	41.0	Cross View Fusion for 3D Human Pose Estimation
GeoFuse	24.6	Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
DeepFuse-Vision Only	32.7	DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image	-

0 of 14 row(s) selected.

3D Human Pose Estimation On Total Capture | SOTA | HyperAI초신경