Communication Dans Un Congrès Année : 2025

A 3D mesh convolution-based autoencoder for geometry compression

Résumé

In this paper, we introduce a novel 3D mesh convolutionbased autoencoder for geometry compression, able to deal with irregular mesh data without requiring neither preprocessing nor manifold/watertightness conditions. The proposed approach extracts meaningful latent representations by learning features directly from the mesh faces, while preserving connectivity through dedicated pooling and unpooling operations. The encoder compresses the input mesh into a compact base mesh space, which ensures that the latent space remains comparable. The decoder reconstructs the original connectivity and restores the compressed geometry to its full resolution. Extensive experiments on multi-class datasets demonstrate that our method outperforms state-of-the-art approaches in both 3D mesh geometry reconstruction and latent space classification tasks.

Fichier principal
Vignette du fichier
ICIP-2025-Germain_BREGEON_et_al.pdf (461.15 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05446276 , version 1 (07-01-2026)

Licence

Identifiants

Citer

Germain Bregeon, Marius Preda, Radu Ispas, Titus Zaharia. A 3D mesh convolution-based autoencoder for geometry compression. 2025 IEEE International Conference on Image Processing (ICIP), Sep 2025, Anchorage, United States. pp.2199-2204, ⟨10.1109/ICIP55913.2025.11084738⟩. ⟨hal-05446276⟩
13 Consultations
87 Téléchargements

Altmetric

Partager

  • More