Open with QR Code
Scan this code to open the model on your device, then, tap on the AR icon
Or, open this link with your mobile:
Loading 3D model
3D viewer is not available.
Learn more here
You are seeing a 360° image instead.
Connection error. Please try again.
Sorry, the model can't be displayed.
Please check out our FAQ to learn how to fix this issue.
It looks like your browser or this site is blocking some scripts or cookies necessary to properly display the viewer.
Or visit the Help Center for more information:
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 gray squares. It is computed from videos taken by a helmet-held DIY multi-camera (four Gopro Hero 3 at 100Hz forming a 360 camera) and by biking 2.5km in a city. The series of gray squares in the streets indicate the camera poses of 5229 keyframes in the videos.
The main steps of the reconstruction method are in my publications: synchronization and 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 enforced in the surface, texturing (IC3D‘20). The input videos are the BikeCity1/BC1 dataset mentioned in BMVC‘16 and CVIU‘17.
The original textures are divided by 3 and are stored in 6 4k texture images. The multi-camera model is central, global shutter, with frame-accurate synchronization.