Communication Dans Un Congrès Année : 2025

MEGA: Masked Generative Autoencoder for Human Mesh Recovery

Résumé

Human Mesh Recovery (HMR) from a single RGB image is a highly ambiguous problem, as an infinite set of 3D interpretations can explain the 2D observation equally well. Nevertheless, most HMR methods overlook this issue and make a single prediction without accounting for this ambiguity. A few approaches generate a distribution of human meshes, enabling the sampling of multiple predictions; however, none of them is competitive with the latest single-output model when making a single prediction. This work proposes a new approach based on masked generative modeling. By tokenizing the human pose and shape, we formulate the HMR task as generating a sequence of discrete tokens conditioned on an input image. We introduce MEGA, a MaskEd Generative Autoencoder trained to recover human meshes from images and partial human mesh token sequences. Given an image, our flexible generation scheme allows us to predict a single human mesh in deterministic mode or to generate multiple human meshes in stochastic mode. Experiments on in-the-wild benchmarks show that MEGA achieves state-of-the-art performance in deterministic and stochastic modes, outperforming single-output and multi-output approaches.

Dates et versions

hal-04980723 , version 1 (06-03-2025)

Identifiants

Citer

Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Francesc Moreno-Noguer. MEGA: Masked Generative Autoencoder for Human Mesh Recovery. CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2025, Nashville (Tennessee), United States. pp.5366-5378, ⟨10.1109/CVPR52734.2025.00505⟩. ⟨hal-04980723⟩
181 Consultations
0 Téléchargements

Altmetric

Partager

  • More