https://scholars.lib.ntu.edu.tw/handle/123456789/632418
標題: | 3D Scene Reconstruction from RGB Images Using Dynamic Graph Convolution for Augmented Reality | 作者: | Weng T.-H Fischer R LI-CHEN FU |
關鍵字: | 3D Scene Understanding; Augmented Reality; Dynamic Graph Convolution | 公開日期: | 2022 | 起(迄)頁: | 638-639 | 來源出版物: | Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 | 摘要: | The 3D scene reconstruction task aims to reconstruct the object shape, object pose, and the 3D layout of the scene. In the field of augmented reality, this information is required for interactions with the surroundings. In this paper, we develop a holistic end-to-end scene reconstruction system using only RGB images. We further designed an architecture that can adapt to different types of objects through our graph convolution network during object surface generation. Moreover, a scene-merging strategy is proposed to alleviate the occlusion problem by merging different views continuously. This also allows our system to reconstruct the complete surroundings in a room. © 2022 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129685439&doi=10.1109%2fVRW55335.2022.00170&partnerID=40&md5=efd4f55f16f929c153c3ee19ed7daa9d https://scholars.lib.ntu.edu.tw/handle/123456789/632418 |
DOI: | 10.1109/VRW55335.2022.00170 | SDG/關鍵字: | Augmented reality; Image reconstruction; Merging; Three dimensional computer graphics; 3D layouts; 3d scene understanding; 3D scenes; 3d scenes reconstruction; Dynamic graph; Dynamic graph convolution; Object pose; Object shape; RGB images; Scene understanding; Convolution |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。