VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space

Résumé

Previous works on Human Pose and Shape Estimation (HPSE) from RGB images can be broadly categorized into two main groups: parametric and non-parametric approaches. Parametric techniques leverage a low-dimensional statistical body model for realistic results, whereas recent non-parametric methods achieve higher precision by directly regressing the 3D coordinates of the human body mesh. This work introduces a novel paradigm to address the HPSE problem, involving a low-dimensional discrete latent representation of the human mesh and framing HPSE as a classification task. Instead of predicting body model parameters or 3D vertex coordinates, we focus on predicting the proposed discrete latent representation, which can be decoded into a registered human mesh. This innovative paradigm offers two key advantages. Firstly, predicting a low-dimensional discrete representation confines our predictions to the space of anthropomorphic poses and shapes even when little training data is available. Secondly, by framing the problem as a classification task, we can harness the discriminative power inherent in neural networks. The proposed model, VQ-HPS, predicts the discrete latent representation of the mesh. The experimental results demonstrate that VQ-HPS outperforms the current state-of-the-art non-parametric approaches while yielding results as realistic as those produced by parametric methods when trained with little data. VQ-HPS also shows promising results when training on large-scale datasets, highlighting the significant potential of the classification approach for HPSE. See the project page at https://g-fiche.github.io/research-pages/vqhps/

Dates et versions

hal-04644818 , version 1 (11-07-2024)

Licence

Identifiants

Citer

Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Antonio Agudo, Francesc Moreno-Noguer. VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space. ECCV 2024 - 18th European Conference on Computer Vision, Sep 2024, Milan, Italy. pp.1-21. ⟨hal-04644818⟩
31 Consultations
0 Téléchargements

Altmetric

Partager

More