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 pair taken by a helmet-held 360 camera (Garmin Virb) and by walking during 12 minutes in a wood. The cones indicate locations and FoV of the camera.
See also a fully textured version (with higher resolution) for several VR headsets at https://maximelhuillier.fr
The 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). See also segments of input videos, geometry and walkthroughs at https://youtu.be/iZjuVDj6Jh4
The original textures are divided by 4 and stored in a 8k texture image. The surface is simplified (edge collapses). The calibration is non-central and global shutter.
1 comment