Human Pose Forecasting On Human36M

评估指标

Average MPJPE (mm) @ 1000 ms

Average MPJPE (mm) @ 400ms

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
Forecast LSTM	149.2	80.8	Intention-based Long-Term Human Motion Anticipation	-
AnyPose1	128.2	80.6	AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations	-
STS-GCN	117.0	65.8	Space-Time-Separable Graph Convolutional Network for Pose Forecasting
LTD-GCN	113.0	63.5	Learning Trajectory Dependencies for Human Motion Prediction
MSR-GCN	114.2	62.9	MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
UNIMASK-M	112.1	61.6	A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis	-
MotionMixer	111.0	59.3	MotionMixer: MLP-based 3D Human Body Pose Forecasting
PGBIG	110.3	58.5	Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
siMLPe	109.4	57.3	Back to MLP: A Simple Baseline for Human Motion Prediction
GraphMixer	108.6	56.7	Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction	-
ResChunk	81.95	56.41	Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
Sun et al.	109.2	55.5	Towards Accurate Human Motion Prediction via Iterative Refinement	-
EqMotion	106.9	55.0	EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
AuxFormer	107	54.1	Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
FMS-AM	-	34.8	Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction	-
MGCN	72.9	34.4	Multi-Graph Convolution Network for Pose Forecasting	-
GCNext	64.7	30.5	GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
BoM	-	-	Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective
STARS	-	-	Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
GSPS	-	-	Generating Smooth Pose Sequences for Diverse Human Motion Prediction

0 of 33 row(s) selected.