Muralikrishnan, S; Chaudhuri, S; Aigerman, N; Kim, VG; Fisher, M; Mitra, NJ; (2022) GLASS: Geometric Latent Augmentation for Shape Spaces. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. (pp. pp. 18531-18540). Institute of Electrical and Electronics Engineers (IEEE)

Preview

Text Muralikrishnan_Glass_Geometric_Latent_Augmentation_for_Shape_Spaces_CVPR_2022_paper.pdf - Accepted Version Download (9MB) | Preview

Abstract

We investigate the problem of training generative models on very sparse collections of 3D models. Particularly, instead of using difficult-to-obtain large sets of 3D models, we demonstrate that geometrically-motivated energy functions can be used to effectively augment and boost only a sparse collection of example (training) models. Technically, we analyze the Hessian of the as-rigid-as-possible (ARAP) energy to adaptively sample from and project to the underlying (local) shape space, and use the augmented dataset to train a variational autoencoder (VAE). We iterate the process, of building latent spaces of VAE and augmenting the associated dataset, to progressively reveal a richer and more expressive generative space for creating geometrically and semantically valid samples. We evaluate our method against a set of strong baselines, provide ablation studies, and demonstrate application towards establishing shape correspondences. Glassproduces multiple interesting and meaningful shape variations even when starting from as few as 3-10 training shapes. Our code is available at https://sanjeevmk.github.io/glass_webpage/.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item