A maximum entropy based data-driven 3D scene generation

DOI10.1142/S1793351X13400047MaRDI QIDQ5408344zbMATH OpenFDO

Authors Mesfin A. Dema, Hamed Sari-Sarraf

Publication date 10 April 2014

Published in International Journal of Semantic Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S1793351X13400047

zbMATH Keywords

maximum entropyMarkov random fieldand-or graphs3D scene generation

Mathematics Subject Classification ID

Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Measures of information, entropy (94A17) Computing methodologies for image processing (68U10)

Recommendations

• Creating consistent scene graphs using a probabilistic grammar
• Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation
• Realistic plant modeling from images based on analysis-by-synthesis
• Random exploration of the procedural space for single-view 3D modeling of buildings
• Multi-view 3D reconstruction and modeling of the unknown 3D scenes using genetic algorithms

Cites work

• A stochastic grammar of images

Cited in

(2)

• FuncScene: function-centric indoor scene synthesis via a variational autoencoder framework
• Creating consistent scene graphs using a probabilistic grammar

This page was built for publication: A maximum entropy based data-driven 3D scene generation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5408344)