DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion

Résumé

We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE. We show that diffusion models enhance the accuracy, robustness, and coherence of human pose estimations. We introduce DiffHPE, a novel strategy for harnessing diffusion models in 3D-HPE, and demonstrate its ability to refine standard supervised 3D-HPE. We also show how diffusion models lead to more robust estimations in the face of occlusions, and improve the time-coherence and the sagittal symmetry of predictions. Using the Human 3.6M dataset, we illustrate the effectiveness of our approach and its superiority over existing models, even under adverse situations where the occlusion patterns in training do not match those in inference. Our findings indicate that while standalone diffusion models provide commendable performance, their accuracy is even better in combination with supervised models, opening exciting new avenues for 3D-HPE research.
Fichier principal
Vignette du fichier
Rommel_DiffHPE_Robust_Coherent_3D_Human_Pose_Lifting_with_Diffusion_ICCVW_2023_paper.pdf (595.54 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04496550 , version 1 (08-03-2024)

Identifiants

Citer

Cédric Rommel, Eduardo Valle, Mickaël Chen, Souhaiel Khalfaoui, Renaud Marlet, et al.. DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion. 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2023), Oct 2023, Paris, France. ⟨10.1109/ICCVW60793.2023.00346⟩. ⟨hal-04496550⟩
18 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More