3D-Aware Motion Generation of Natural Objects in a Single Omnidirectional Image for Virtual Sightseeing
Year: 2025
Type: article
Abstract: Services using omnidirectional images have become increasingly popular for virtual sightseeing. For example, Google Street View enables users to view the scenery of a location online without physically visiting it. However, the use of still images in such services limits the sense of presence. This study proposes a method that focuses on natural elements such as water, sky, and trees in a single omnidirectional image and reproduces their motion in 3D space, generating omnidirectional videos to improve the sense of reality in virtual sightseeing. Experiments demonstrate the effectiveness of the proposed method through comparison with a conventional method and user studies.
Authors: Norihiko KAWAI, Motoki KAKUHO
Institution: Osaka Institute of Technology
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4417409015