A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation

Résumé

We propose a new loss function that we call Laplacian loss, based on spatio-temporal Laplacian representation of the motion as a graph. This loss function is intended to be used in training models for motion reconstruction through 3D human pose estimation from videos. It compares the differential coordinates of the joints obtained from the graph representation of the ground truth against the one of the estimation. We design a fully convolutional temporal network for motion reconstruction to achieve better temporal consistency of estimation. We use this generic model to study the impact of our proposed loss function on the benchmarks provided by Human3.6M. We also make use of various motion descriptors such as velocity, acceleration to make a thorough evaluation of the temporal consistency while comparing the results to some of the state-of-the-art solutions.
Fichier principal
Vignette du fichier
paper.pdf (5.73 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03966941 , version 1 (01-02-2023)

Identifiants

  • HAL Id : hal-03966941 , version 1

Citer

Mansour Tchenegnon, Sylvie Gibet, Thibaut Le Naour. A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation. European Conference on Computer Vision (ECCV 2022), Workshop on What is Motion for?, Oct 2022, Tel Aviv, Israel. ⟨hal-03966941⟩
20 Consultations
50 Téléchargements

Partager

Gmail Facebook X LinkedIn More