1 / 20

Feature Sensitive Bas Relief Generation

Feature Sensitive Bas Relief Generation. Jens Kerber 1 , Art Tevs 1 , Alexander Belyaev 2 , Rhaleb Zayer 3 , and Hans-Peter Seidel 1 1 Max-Planck- Instut f ü r Informatik, Saarbr ü cken 2 Joint Research Institute for Image and Signal Processing, Edinburgh

bess
Download Presentation

Feature Sensitive Bas Relief Generation

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. Feature Sensitive Bas Relief Generation Jens Kerber1, Art Tevs1, Alexander Belyaev2, RhalebZayer3, andHans-Peter Seidel1 1 Max-Planck-Instut für Informatik, Saarbrücken 2 Joint Research Institute for Image and Signal Processing, Edinburgh 3 LORIA-INRIA Loraine, CNRS, Nancy

  2. Motivation • Aim • Compress depth-interval size of height field • No loss of important features • Applications for Bas-Reliefs • Coinage • Packaging • Shape Decoration • Embossment • Engraving • Carving • DisplacementMaps 1 2 1 http://www.cachecoins.org/ 2Real-time relief mapping on arbitrary polygonal surfaces Policarpo F., Oliveira M., Comba J. L. D., SIGGRAPH 2005 SMI 2009, Tsinghua University, Beijing, China

  3. Naïve Approach • Linear Rescaling SMI 2009, Tsinghua University, Beijing, China

  4. Related Work • Automatic generation of bas-reliefs from 3D shapesW. Song, A. Belyaev, H.-P. Seidel, SMI 2007 (short paper) + Introducing the problem and attempting to solve it • Digital Bas-Relief from 3D Scenes T. Weyrich, J. Deng, C. Barnes, S. Rusinkiewicz, A. Finkelstein, SIGGRAPH 2007 + Impressive results - Much user interaction required, computationally expensive • Feature Preserving Depth Compression of Range Images J. Kerber, A. Belyaev, H.-P. Seidel, SCCG 2007 + Simple and fast - Spherical parts not well reproduced, problems with noise • Bas-Relief Generation Using Adaptive Histogram Equalization X. Sun, P. Rosin, R. Martin, TVCG 2009 + Very good results - Time consuming SMI 2009, Tsinghua University, Beijing, China

  5. Pipeline Outlier Detection Gradient Extraction Silhouette Removal Attenuation I Rescaling Re-assembling Re-weighting Decompo sition R SMI 2009, Tsinghua University, Beijing, China

  6. Silhouette Treatment • Gradient of the Background mask = 1 ? SMI 2009, Tsinghua University, Beijing, China

  7. Outlier Detection • Tollerance parameter • Deviation to mean gradient value SMI 2009, Tsinghua University, Beijing, China

  8. Signal Decomposition • Base-layer and Detail-layer • Detail Enhancement • Base Compression SMI 2009, Tsinghua University, Beijing, China

  9. Bilateral Filter Gradient domain Spatial Domain Preservation of ridges and valleys Curvature extrema preservation • Edge preservation • Gradient extrema preservation SMI 2009, Tsinghua University, Beijing, China

  10. Reweighting Before After • X-Gradient • Y-Gradient SMI 2009, Tsinghua University, Beijing, China

  11. PoissonReconstruction • Given Ix, Iy • Compute Ixx + Iyy = ΔI • Partial Differential Equation • Well studied Problem • Multi-Grid-Solver • Assumption: Frame equals background SMI 2009, Tsinghua University, Beijing, China

  12. Results SMI 2009, Tsinghua University, Beijing, China

  13. Cubism • Ancient technique in art • Combine multiple viewpoints in a single painting • Aim: extend this effect from 2D to sculpting 3 3 SMI 2009, Tsinghua University, Beijing, China 3 http://picasso.tamu.edu/picasso/

  14. Height Field Capturing • Open GL Application • 180˚ in 15˚ steps • Composition in 2D 30 75 0 -75 -30 SMI 2009, Tsinghua University, Beijing, China

  15. Transition Problems • Transition areas • Seams are automatically detected as outliers • But set to 0 • Flat transitions would emphazise the impression of having two different parts SMI 2009, Tsinghua University, Beijing, China

  16. Transition Problems (ctd.) • 0-Gradient affects 3x3 neighborhood • Re-fill affected area • Weighted average (Gauss) excluding masked entries • Seamless results SMI 2009, Tsinghua University, Beijing, China

  17. Results SMI 2009, Tsinghua University, Beijing, China

  18. Performance • Intel 4x2.6 GHz, 8GB, Matlab64 Implementation • Bottleneck • Bilateral Filter • Poisson Reconstruction • Not optimized yet, possible acceleration SMI 2009, Tsinghua University, Beijing, China

  19. Conclusion • Contribution • Little userintervention • Preservation of fine and sharp structural details • More artisticfreedom • Potentially Fast • Independent of complexity • Commercial applications SMI 2009, Tsinghua University, Beijing, China

  20. Future work • Dynamic extension • Video • Thank you for your attention! SMI 2009, Tsinghua University, Beijing, China

More Related