Learning geometry-aware joint latent space for simultaneous multimodal shape generation

DOI10.1016/J.CAGD.2022.102076MaRDI QIDQ2127700zbMATH OpenOpenAlexFDO

Authors Artem Komarichev, Jing Hua, Zichun Zhong

Publication date 21 April 2022

Published in Computer Aided Geometric Design (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.cagd.2022.102076

zbMATH Keywords

cross-modality shapegeometry-awarenessjoint latent spacemultimodal shape

Mathematics Subject Classification ID

Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Recommendations

• Shape part transfer via semantic latent space factorization
• Quantitative and flexible 3D shape dataset augmentation via latent space embedding and deformation learning
• Inferring 3D shapes from image collections using adversarial networks
• Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation
• Learning single-image 3D reconstruction by generative modelling of shape, pose and shading

Cites work

• Deep learning
• Estimating surface normals in noisy point cloud data
• Large scale image annotation: learning to rank with joint word-image embeddings
• Particle-based anisotropic surface meshing
• The earth mover's distance as a metric for image retrieval
• Visualizing data using t-SNE

Cited in

(5)

• Quantitative and flexible 3D shape dataset augmentation via latent space embedding and deformation learning
• Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation
• Shape part transfer via semantic latent space factorization
• Geometric Multimodal Learning Based on Local Signal Expansion for Joint Diagonalization
• Point-styleGAN: multi-scale point cloud synthesis with style modulation

Describes a project that uses

Uses Software

• KPConv
• GRAF
• PointNet
• EMD
• MeshCNN
• PointCNN
• FoldingNet
• Wasserstein GAN
• t-SNE

This page was built for publication: Learning geometry-aware joint latent space for simultaneous multimodal shape generation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2127700)