VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder

Tejas Anvekar, Ramesh Ashok Tabib, Dikshit Hegde, Uma Mudengudi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2978-2985


In this paper, we propose VG-VAE: Venatus Geometric Variational Auto-Encoder for capturing unsupervised hierarchical local and global geometric signatures in pointcloud. Recent research emphasises the significance of the underlying intrinsic geometry for pointcloud processing. Our contribution is to extract and analyse the morphology of the pointcloud using the proposed Geometric Proximity Correlator (GPC) and variational sampling of the latent. The extraction of local geometric signatures is facilitated by the GPC, whereas the extraction of global geometry is facilitated by variational sampling. Furthermore, we apply a naive mix of vector algebra and 3D geometry to extract the basic per-point geometric signature, which assists the unsupervised hypothesis. We provide statistical analyses of local and global geometric signatures. The impacts of our geometric features are demonstrated on pointcloud classification as downstream task using the classic pointcloud feature extractor PointNet. We demonstrate our analysis on ModelNet40 a benchmark dataset, and compare with state-of-the-art techniques.

Related Material

@InProceedings{Anvekar_2022_CVPR, author = {Anvekar, Tejas and Tabib, Ramesh Ashok and Hegde, Dikshit and Mudengudi, Uma}, title = {VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2978-2985} }