1. Yizhou Yu Texture-Mapping Real Scenes from Photographs Yizhou Yu Computer Science Division University of California at Berkeley Yizhou Yu Computer Science Division University of California at Berkeley SIGGRAPH 2000 Course on Image-Based Surface Details

2. Yizhou Yu Basic Steps Acquire Photographs Recover Geometry Align Photographs with Geometry Map Photographs onto Geometry Acquire Photographs Recover Geometry Align Photographs with Geometry Map Photographs onto Geometry

3. Yizhou Yu Camera Pose Estimation Input –Known geometry recovered from photographs or laser range scanners –A set of photographs taken with a camera Output –For each photograph, 3 rotation and 3 translation parameters of the camera with respect to the geometry Requirement –4 correspondences between each photograph and the geometry Input –Known geometry recovered from photographs or laser range scanners –A set of photographs taken with a camera Output –For each photograph, 3 rotation and 3 translation parameters of the camera with respect to the geometry Requirement –4 correspondences between each photograph and the geometry

4. Yizhou Yu Recover Camera Pose with Known Correspondences Least-squares solution –Needs good initial estimation from human interaction Camera Image

5. Yizhou Yu Recover Rotation Parameters only from Known Correspondences Constraints Least-squares solution Camera Image

6. Yizhou Yu Obtaining Correspondences Feature Detection in 3D geometry and 2D images Human interaction –Interactively pick corresponding points in photographs and 3D geometry Automatic Search –Combinatorial search Feature Detection in 3D geometry and 2D images Human interaction –Interactively pick corresponding points in photographs and 3D geometry Automatic Search –Combinatorial search

7. Yizhou Yu Automatic Search for Correspondences Pose estimation using calibration targets Combinatorial search for the best match –4 correspondences each image Pose estimation using calibration targets Combinatorial search for the best match –4 correspondences each image 3D Targets

8. Yizhou Yu Camera Pose Results Accuracy: consistently within 2 pixels Texture-mapping a single image

9. Yizhou Yu Texture Mapping Conventional texture-mapping with texture coordinates Projective texture-mapping Conventional texture-mapping with texture coordinates Projective texture-mapping

10. Yizhou Yu Texture Map Synthesis I Conventional Texture- Mapping with Texture Coordinates –Create a triangular texture patch for each triangle –The texture patch is a weighted average of the image patches from multiple photographs –Pixels that are close to image boundaries or viewed from a grazing angle obtain smaller weights Photograph Texture Map 3D Triangle

11. Yizhou Yu Texture Map Synthesis II Allocate space for texture patches from texture maps –Generalization of memory allocation to 2D –Quantize edge length to a power of 2 –Sort texture patches into decreasing order and use First-Fit strategy to allocate space Allocate space for texture patches from texture maps –Generalization of memory allocation to 2D –Quantize edge length to a power of 2 –Sort texture patches into decreasing order and use First-Fit strategy to allocate space First-Fit

12. Yizhou Yu A Texture Map Packed with Triangular Texture Patches

13. Yizhou Yu Texture-Mapping and Object Manipulation Original ConfigurationNovel Configuration

14. Yizhou Yu Texture Map Compression I The size of each texture patch is determined by the amount of color variations on its corresponding triangles in photographs. An edge detector (the derivative of the Gaussian) is used as a metric for variations. The size of each texture patch is determined by the amount of color variations on its corresponding triangles in photographs. An edge detector (the derivative of the Gaussian) is used as a metric for variations.

15. Yizhou Yu Texture Map Compression II Reuse texture patches –Map the same patch to multiple 3D triangles with similar color variations K-means clustering to generate texture patch representatives Larger penalty along triange edges to reduce Mach Band effect Texture Map 3D Triangles

16. Yizhou Yu Synthetic Images with Compressed and Uncompressed Texture Maps Uncompressed 20 texture maps Compressed 5 texture maps 20 texture maps5 texture maps

17. Yizhou Yu Projective Texture-Mapping Can directly use the original photographs in texture-mapping Visibility processing is more complicated Projective texture-mapping has been implemented in hardware, therefore, real-time rendering becomes possible View-dependent effects can be added by effectively using hardware accumulation buffer Can directly use the original photographs in texture-mapping Visibility processing is more complicated Projective texture-mapping has been implemented in hardware, therefore, real-time rendering becomes possible View-dependent effects can be added by effectively using hardware accumulation buffer

18. Yizhou Yu Motivation for Visibility Processing: Artifacts Caused by Hardware Camera Image Geometry Texture gets projected onto occluded and backfacing polygons

19. Yizhou Yu Visibility Algorithms Image-space algorithms –Shadow buffer –Ray casting Object-space algorithms –Weiler-Atherton Image-space algorithms –Shadow buffer –Ray casting Object-space algorithms –Weiler-Atherton

20. Yizhou Yu A Hybrid Visibility Algorithm Occlusion testing in image-space using Z- buffer hardware –Render polygons with their identifiers as colors –Retrieve occluding polygons’ ids from color buffer Object-space shallow clipping to generate fewer polygons Occlusion testing in image-space using Z- buffer hardware –Render polygons with their identifiers as colors –Retrieve occluding polygons’ ids from color buffer Object-space shallow clipping to generate fewer polygons

21. Yizhou Yu Input Photographs and Recovered Geometry from Facade

22. Yizhou Yu Visibility Processing Results The towerThe rest of the campus

23. Yizhou Yu Synthetic Renderings

24. Yizhou Yu

25. Camera Image Needs good initial estimation

26. Yizhou Yu Camera Image