A 3D mesh convolution-based autoencoder for geometry compression
This addresses geometry compression for 3D mesh applications, offering a novel method for a known bottleneck.
The paper tackles the problem of compressing 3D mesh geometry by introducing a 3D mesh convolution-based autoencoder that handles irregular meshes without preprocessing, outperforming state-of-the-art methods in reconstruction and classification tasks.
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. Code available at: github.com/germainGB/MeshConv3D