TY - GEN
T1 - A 3D MESH CONVOLUTION-BASED AUTOENCODER FOR GEOMETRY COMPRESSION
AU - Bregeon, Germain
AU - Preda, Marius
AU - Ispas, Radu
AU - Zaharia, Titus
N1 - Publisher Copyright:
©2025 IEEE.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - In this paper, we introduce a novel 3D mesh convolution-based 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.
AB - In this paper, we introduce a novel 3D mesh convolution-based 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.
KW - Mesh autoencoder
KW - mesh convolution
KW - mesh geometry compression
KW - mesh reconstruction
UR - https://www.scopus.com/pages/publications/105028600970
U2 - 10.1109/ICIP55913.2025.11084738
DO - 10.1109/ICIP55913.2025.11084738
M3 - Conference contribution
AN - SCOPUS:105028600970
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2199
EP - 2204
BT - 2025 IEEE International Conference on Image Processing, ICIP 2025 - Proceedings
PB - IEEE Computer Society
T2 - 32nd IEEE International Conference on Image Processing, ICIP 2025
Y2 - 14 September 2025 through 17 September 2025
ER -