Presentation is loading. Please wait.

Presentation is loading. Please wait.

SmartBoxes for Interactive Urban Reconstruction Liangliang Nan 1, Andrei Sharf 1, Hao Zhang 2, Daniel Cohen-Or 3, Baoquan Chen 1 1 Shenzhen Institutes.

Similar presentations


Presentation on theme: "SmartBoxes for Interactive Urban Reconstruction Liangliang Nan 1, Andrei Sharf 1, Hao Zhang 2, Daniel Cohen-Or 3, Baoquan Chen 1 1 Shenzhen Institutes."— Presentation transcript:

1 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

2 Virtual BerlinVirtual Philadelphia 3D Cities

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

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

5 Outdoor Urban Scanning

6

7 Imperfect Scans - Occlusions Point cloud contains holes due to various occlusions (shadows)

8 Imperfect Scans – Angle & Range Oblique scanning angle Laser energy attenuation on range

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

10 SmartBoxes Box-up and Smart!

11 SmartBoxes Box prior shape fitting Smart context awareness Both Context Data

12 Live Demo

13 9

14 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]

15 Preprocessing Automatic detection of planes and edges assuming dominant orthogonal axes –RANSAC planes –Line sweep edges

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

17 Data fitting D(B,P) snap FacetEdge Data fitting force Data quality ( Confidence + Density ) Distance

18 Grouping Simple SmartBox Compound SmartBox Align to remove gaps and intersections –cluster and align close to co-linear edges

19 Drag-and-drop context C(B i-1, B i ) The context of B i B i-1 B i-2 B i-3 IntervalAlignmentScale Context BiBi

20 Drag-and-drop context C(B i-1, B i ) The context of B i –Interval term B i-1 B i-2 B i-3 BiBi

21 Drag-and-drop context C(B i-1, B i ) The context of B i –Alignment term BiBi B i-1 B i-2 B i-3

22 BiBi Drag-and-drop context C(B i-1, B i ) The context of B i –Scale term BiBi B i-1 B i-2 B i-3

23 Discrete objective minimization Find linear transformation T(excluding rotation) to minimize: Data fitting forceContextual force

24 Discrete objective minimization B i-1 B i-2 B i-3 Find linear transformation T(excluding rotation) to minimize: Data fitting forceContextual force

25 Balance between two forces

26 Emerging city of Shenzhen, China

27 Results: textured buildings

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

29 (Thank You)!


Download ppt "SmartBoxes for Interactive Urban Reconstruction Liangliang Nan 1, Andrei Sharf 1, Hao Zhang 2, Daniel Cohen-Or 3, Baoquan Chen 1 1 Shenzhen Institutes."

Similar presentations


Ads by Google