NAVE	Networked Augmented Virtual Environment (NAVE) Group

Publication:Zhong Zhou, Ming Meng, Yi Zhou, Zhe Zhu and Jingdi You. Model-Guided 3D Stitching for Augmented Virtual Environment[J]. SCIENCE CHINA Information Sciences, 66(1), 112106 (2023) (CCF-A Journal, IF:7.275) pdf         Image and video stitching have made tremendous progress in the construction of wide fieldof-view (FOV). However, some long-term challenges still exist, including wide baselines between cameras, large parallaxes, and low texture in overlapping areas. Augmented virtual environment (AVE) captures videos as live textures of 3D models in a virtual environment, and provides another 3D solution to overcome the aforementioned challenges. Existing AVE methods primarily follow from video projection, and cannot produce satisfactory stitching results compared with image stitching. In this paper, we propose a novel model-guided 3D stitching algorithm for AVE. The algorithm recovers an approximate 3D model for each video streaming and optimizes the warping of the models to meet the requirements of all feature points matching with the 3D models in the adjacent videos. Compared with state-of-the-art methods, experiment results illustrate that our method significantly improves the stitching quality. create by admin at 2021-10-18 23:12:30