FuncScene: function-centric indoor scene synthesis via a variational autoencoder framework

DOI10.1016/J.CAGD.2024.102319MaRDI QIDQ6563949FDO

Authors Wenjie Min, Wenming Wu, Gaofeng Zhang, Liping Zheng

Publication date 28 June 2024

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

zbMATH Keywords

generative modelneural networkfunction groupindoor scene synthesis

Mathematics Subject Classification ID

Numerical approximation and computational geometry (primarily algorithms) (65Dxx)

Recommendations

• A maximum entropy based data-driven 3D scene generation
• Global-affine and local-specific generative adversarial network for semantic-guided image generation
• Point-styleGAN: multi-scale point cloud synthesis with style modulation
• Coarse-to-fine segmentation for indoor scenes with progressive supervision
• Generated realistic noise and rotation-equivariant models for data-driven mesh denoising

Cites work

• Creating consistent scene graphs using a probabilistic grammar

Cited in

(1)

• Point-styleGAN: multi-scale point cloud synthesis with style modulation

This page was built for publication: FuncScene: function-centric indoor scene synthesis via a variational autoencoder framework

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6563949)