Shallow2Deep: Indoor scene modeling by single image understanding
作者：
Highlights：
• An automatic scene understanding and modeling approach on a single indoor image with a shallow-to-deep convolutional architecture.
• An image-based Relation Network to learn support relationship between indoor objects and improve our scene modeling quality and plausibility.
• A global optimization strategy to incorporates the outputs from former networks and recover 3D scenes in a contextually consistent approach.
摘要
•An automatic scene understanding and modeling approach on a single indoor image with a shallow-to-deep convolutional architecture.•An image-based Relation Network to learn support relationship between indoor objects and improve our scene modeling quality and plausibility.•A global optimization strategy to incorporates the outputs from former networks and recover 3D scenes in a contextually consistent approach.
论文关键词：Scene understanding,Image-based modeling,Semantic modeling,Relational reasoning
论文评审过程：Received 29 June 2019, Revised 30 January 2020, Accepted 11 February 2020, Available online 12 February 2020, Version of Record 28 February 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107271
