This model is best viewed by selecting the first person mode in navigation setting and slow speed (eg 0 or 1) and navigating at the neighborhood of the series of small gray cones. It is computed from a video taken by a helmet-held 360 camera (Gopro Max) and by walking during 509 seconds. The cones indicate locations of the camera.
See also the higher res. and fully textured version for several VR headsets available at https://maximelhuillier.fr
The main steps of the reconstruction method are in my publications: self-calibration (3DV‘15, CVIU‘17), structure-from-motion (BMVC‘07, IVC‘09), surface reconstruction (CVIU‘18 improved by IC3D‘19), curves are matched (PAMI‘02) and integrated in the surface, texturing (IC3D‘20), coordinate reset (IC3D‘21).
The original textures are divided by 3. The surface is simplified (edge collapses). The multi-camera model is non-central and global shutter.
Here is an image of the input video
Comments