25% OFF 3D Models - Use code SUMMERISCOMING shop now
0
Login
0
0%

Loading 3D model

Model Inspector
00:00.00

    Select an annotation

    It looks like your browser or this site is blocking some scripts or cookies necessary to properly display the viewer.

    View this model on Sketchfab :
    https://sketchfab.com/models/297e85e684144f38946a1577e44ccfd9/embed?utm_source=website&utm_campaign=blocked_scripts_error

    Or visit the Help Center for more information:
    https://help.sketchfab.com/hc/en-us/articles/203059088-Compatibility?utm_source=website&utm_campaign=blocked_scripts_error#troubleshooting-scripts

    2.5km street, helmet-held 360 camera 3D Model

    17.1k
    17.1k Views
    Triangles: 3.2M
    Vertices: 1.6M
    More model 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 2615 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‘13 improved by ICPR‘14), curves are matched (PAMI‘02) and enforced in the surface. The input videos are the BikeCity1/BC1 dataset mentioned in BMVC‘16 and CVIU‘17.

    The original textures are divided by 3 (or 4 for the sky) and are stored in a 8k texture image. The multi-camera model is central, global shutter, with frame-accurate synchronization.

    Published
    September 19th 2017
    No category set.
    No tags set.
    Show
    In collections
    Suggested 3D models