1 / 29

SmartBoxes for Interactive Urban Reconstruction

SmartBoxes for Interactive Urban Reconstruction. Liangliang Nan 1 , Andrei Sharf 1 , Hao Zhang 2 , Daniel Cohen-Or 3 , Baoquan Chen 1 1 Shenzhen Institutes of Advanced Technology (SIAT), China 2 Simon Fraser University, Canada 3 University of Tel Aviv, Israel. 3D Cities.

kineta
Download Presentation

SmartBoxes for Interactive Urban Reconstruction

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. SmartBoxes for Interactive Urban Reconstruction Liangliang Nan1, Andrei Sharf1, Hao Zhang2, Daniel Cohen-Or3, Baoquan Chen1 1 Shenzhen Institutes of Advanced Technology (SIAT), China 2 Simon Fraser University, Canada 3University of Tel Aviv, Israel

  2. 3D Cities Virtual Philadelphia Virtual Berlin

  3. Acquisition of Urban Environments Remote Sensing Systems Airborne LIDAR Cameras/videos Auto-mounted LIDAR 3D Digital City

  4. 3D LiDAR scanner • Street-level • 60km/h • 180 pitch • [100-300m] range • 100K points/second • 5cm XY accuracy

  5. Outdoor Urban Scanning

  6. Imperfect Scans - Occlusions • Point cloud contains holes due to various occlusions (“shadows”)

  7. Imperfect Scans – Angle & Range • Oblique scanning angle • Laser energy attenuation on range

  8. Urban Building Characteristics • Dominant planes • Repetitions, intra symmetry and regularity • Axis-aligned basic primitives

  9. SmartBoxes • Box-up and Smart!

  10. SmartBoxes • Box prior shape fitting • Smart context awareness Data Context Both

  11. Live Demo

  12. Related Work • Procedural modeling of buildings and facades [Wonka2003;Muller2007] • Automatic 3D reconstruction from 2D images [Zisserman2002;Xiao2009;Furukawa2009] • Interactive modeling of architectural structures [Debevec1996;Schindler2003; Xiao2008;Sinha2008;Jiang2009] • Primitive fitting to data [Gal2007;Schnabel 2009]

  13. Preprocessing • Automatic detection of planes and edges assuming dominant orthogonal axes • RANSAC planes • Line sweep edges

  14. Snapping a Box • 2D rubber band ROI • Collect planes, edges, corners • Find the best fitting box using data fitting force D(B,P)

  15. Data fitting D(B,P) snap • Data fitting force Facet Edge Data quality (Confidence + Density) Distance

  16. Grouping • Simple SmartBox Compound SmartBox • Align to remove gaps and intersections • cluster and align close to co-linear edges

  17. Drag-and-drop context C(Bi-1, Bi) • The context of Bi Interval Alignment Scale ••• Bi Bi-3 Bi-2 Bi-1 Context

  18. Drag-and-drop context C(Bi-1, Bi) • The context of Bi • Interval term ••• Bi Bi-3 Bi-2 Bi-1

  19. Drag-and-drop context C(Bi-1, Bi) • The context of Bi • Alignment term ••• Bi-3 Bi-2 Bi-1 Bi

  20. Drag-and-drop context C(Bi-1, Bi) • The context of Bi • Scale term ••• Bi-3 Bi-2 Bi-1 Bi Bi

  21. Discrete objective minimization • Find linear transformation T(excluding rotation) to minimize: Data fitting force Contextual force

  22. Discrete objective minimization • Find linear transformation T(excluding rotation) to minimize: Data fitting force Contextual force ••• Bi-3 Bi-2 Bi-1

  23. Balance between two forces

  24. Emerging city of Shenzhen, China

  25. Results: textured buildings

  26. Habitat 67 (Montreal, Canada) The Crooked House (Sopot, Poland) Manchester Civil Justice Centre (Manchester, UK)

  27. (Thank You)!

More Related