Learning 3D semantic scene graphs with instance embeddings

DOI10.1007/S11263-021-01546-9zbMATH Open1491.68250OpenAlexW4206996644MaRDI QIDQ2118429FDOQ2118429

Authors: Johanna Wald, Nassir Navab, Federico Tombari 

Publication date: 22 March 2022

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-021-01546-9

Recommendations

• Creating consistent scene graphs using a probabilistic grammar
• Pix2Shape: towards unsupervised learning of 3D scenes from images using a view-based representation
• Coarse-to-fine segmentation for indoor scenes with progressive supervision
• Learning point cloud shapes with geometric and topological structures
• Indexing 3D Scenes Using the Interaction Bisector Surface

zbMATH Keywords

semantic segmentation3D scene understandingscene graphs

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Visualizing data using t-SNE
• A survey of content-based image retrieval with high-level semantics
• Creating consistent scene graphs using a probabilistic grammar

Cited In (1)

• 3D Randomized Connection Network With Graph-Based Label Inference

Uses Software

• WordNet
• TensorFlow
• k-means++
• t-SNE
• PointNet
• PointCNN
• MS-COCO
• Visual Genome
• BiggerPicture
• U-Net
• GitHub
• Cityscapes
• ScanNet
• RGCNN
• NYU Depth
• YFCC100M
• KPConv
• Faster R-CNN
• MinkowskiEngine

This page was built for publication: Learning 3D semantic scene graphs with instance embeddings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2118429)