Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Human Pose Forecasting On Amass

Metriken

ADE

APD

FDE

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	ADE	APD	FDE	Paper Title	Repository
ThePoseKnows	0.656	9.283	0.675	The Pose Knows: Video Forecasting by Generating Pose Futures
STS-GCN	-	-	-	Space-Time-Separable Graph Convolutional Network for Pose Forecasting
AnyPose1	-	-	-	AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations	-
siMLPe	-	-	-	Back to MLP: A Simple Baseline for Human Motion Prediction
Dlow	0.590	13.170	0.612	DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
BeLFusion	0.513	9.376	0.560	BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
TransFusion	0.508	8.853	0.568	TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction
GCNext	-	-	-	GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
GSPS	0.563	12.465	0.613	Generating Smooth Pose Sequences for Diverse Human Motion Prediction
TCD	-	-	-	A generic diffusion-based approach for 3D human pose prediction in the wild
Sun et al.	-	-	-	Towards Accurate Human Motion Prediction via Iterative Refinement	-

0 of 11 row(s) selected.