Shallow2Deep: Indoor scene modeling by single image understanding

Authors: Nie, Y., Guo, S., Chang, J., Han, X., Huang, J., Hu, S.-M. and Zhang, J.

http://eprints.bournemouth.ac.uk/33683/

Journal: Pattern Recognition

Volume: 103

Publisher: Elsevier

ISSN: 0031-3203

DOI: 10.1016/j.patcog.2020.107271

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a single RGB image, our method simultaneously recovers semantic contents, 3D geometry and object relationship by reasoning indoor environment context. Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling. It involves multi-level convolutional networks to parse indoor semantics/geometry into non-relational and relational knowledge. Non-relational knowledge extracted from shallow-end networks (e.g. room layout, object geometry) is fed forward into deeper levels to parse relational semantics (e.g. support relationship). A Relation Network is proposed to infer the support relationship between objects. All the structured semantics and geometry above are assembled to guide a global optimization for 3D scene modeling. Qualitative and quantitative analysis demonstrates the feasibility of our method in understanding and modeling semantics-enriched indoor scenes by evaluating the performance of reconstruction accuracy, computation performance and scene complexity.

This data was imported from Scopus:

Authors: Nie, Y., Guo, S., Chang, J., Han, X., Huang, J., Hu, S.M. and Zhang, J.J.

http://eprints.bournemouth.ac.uk/33683/

Journal: Pattern Recognition

Volume: 103

ISSN: 0031-3203

DOI: 10.1016/j.patcog.2020.107271

© 2020 Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a single RGB image, our method simultaneously recovers semantic contents, 3D geometry and object relationship by reasoning indoor environment context. Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling. It involves multi-level convolutional networks to parse indoor semantics/geometry into non-relational and relational knowledge. Non-relational knowledge extracted from shallow-end networks (e.g. room layout, object geometry) is fed forward into deeper levels to parse relational semantics (e.g. support relationship). A Relation Network is proposed to infer the support relationship between objects. All the structured semantics and geometry above are assembled to guide a global optimization for 3D scene modeling. Qualitative and quantitative analysis demonstrates the feasibility of our method in understanding and modeling semantics-enriched indoor scenes by evaluating the performance of reconstruction accuracy, computation performance and scene complexity.

This data was imported from Web of Science (Lite):

Authors: Nie, Y., Guo, S., Chang, J., Han, X., Huang, J., Hu, S.-M. and Zhang, J.J.

http://eprints.bournemouth.ac.uk/33683/

Journal: PATTERN RECOGNITION

Volume: 103

eISSN: 1873-5142

ISSN: 0031-3203

DOI: 10.1016/j.patcog.2020.107271

The data on this page was last updated at 05:26 on October 22, 2020.