Scene Transformer: Automatic Transformation from Real Scene to Virtual Scene

Runze Fan, Lili Wang, Chan Tong Lam, Wei Ke

研究成果: Conference contribution同行評審

摘要

Given a real scene and a virtual scene, the indoor scene transformation problem is defined as transforming the layout of the input virtual scene. The transformed layout preserves as much as possible the relationship between the furniture in the input virtual scene, and the input real scene provides the user with as much passive haptic as possible when exploring the virtual scene. We propose a real-scene-constrained deep scene transformer to solve this problem. First, we introduce the deep scene matching network to predict the matching relationship between real furniture and virtual furniture. Then we introduce a layout refinement algorithm based on the refinement parameter network to arrange the matched virtual furniture into the new virtual scene. At last, we introduce a deep scene generating network to arrange the unmatched virtual furniture into the new virtual scene.

原文English
主出版物標題Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面885-886
頁數2
ISBN(電子)9798350348392
DOIs
出版狀態Published - 2023
事件2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 - Shanghai, China
持續時間: 25 3月 202329 3月 2023

出版系列

名字Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

Conference

Conference2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
國家/地區China
城市Shanghai
期間25/03/2329/03/23

指紋

深入研究「Scene Transformer: Automatic Transformation from Real Scene to Virtual Scene」主題。共同形成了獨特的指紋。

引用此