1. Image-Based Rendering

2. 3D Scene = Shape + Shading Source: Leonard mcMillan, UNC-CH

3. Modeling is Hard! Good 3D geometric models need a lot of work. Getting correct material properties is even harder: –R, G, B, Ka, Kd, Ks, specularity for Phong model. –BRDF –Subsurface reflectance, diffraction…etc.

4. How to Create 3D Contents AutoCAD: used for architectures (buildings) 3D Studio Max, Blender…etc. Maya is a major production tool used in movie studios. Problems? It takes an artist, and it’s still hard to make it look real!

5. QuickTime VR

6. 3D Photography Can building 3D models be as easy as taking 2D photos? How do we digitize the massive assets in various museums? –QuickTime VR object movies –3D Scans: Cyberware scanner, Digital Michelangeo Source: www.cyberware.com

7. Image-Based Rendering Can we build 3D contents from photographs directly? –Difference from computer vision? Can we make the objects look more real? –Difference from texture mapping?

8. Top Level Survey 3D Graphics Image-Based Rendering & Modeling Geometry or Surface Based Rendering & Modeling Sample-Based Graphics Volume Rendering

9. Traditional Computer Graphics Input: Geometry, Material Properties (Color, Reflectance, … etc.), Lighting. Transformation and Rasterization. Transform (& Lighting) Rasterization 3D Graphics Pipeline

10. Role of Images Used as textures. Or, as input to computer vision methods in order to recover the 3D models. 3D Graphics Pipeline Vision

11. Image-Based Rendering To bypass the 3D models altogether. 3D Graphics Pipeline Vision Image-Based Rendering

12. Input: Regular Images or “ Depth Images." No 3D model is constructed. Example: 3D Warping.

13. 3D Warping: Another Example Reading room of UNC CS department –Source images contain depths in each pixel. –The depths are obtained from a laser range finder.

14. Why IBR? Problems of triangle-based graphics: –Always starts from scratch. –Millions of sub-pixel triangles. GeometryIBR ModelingDifficultEasy Complexity#triangles#pixels FidelitySyntheticAcquired

15. Why is It Possible? 5D Plenoptic Function. –Color = f(x, y, z, ,  ) –(x, y, z) defines the viewpoint. –( ,  ) defines the view direction. 4D Light Field/Lumigraph –Color = f(u, v, s, t) –(u, v) defines the viewpoint. –(s, t) defines the pixel coord. Picture source: Leonard McMillan

16. –Each pixel in the source images has coordinates (u 1, v 1 ), depth info  1, and color. –Warping Equation is applied to each pixel (u 2, v 2 ) = f(u 1, v 1,  1 ) = ( a  u 1 +b  v 1 +c+d  1, e  u 1 +f  v 1 +g+h  1 ) i  u 1 +j  v 1 +k+ l  1 i  u 1 +j  v 1 +k+ l  1 where variables a to l are fixed for the same view. –Rendering Time = O(#pixels) 3D Image Warping

18. u1u1 v1v1 u2u2 v2v2

19. Artifacts of 3D Image Warping Surfaces that were occluded in source images. Non-uniform sampling (an example in the next slide).

20. Reconstruction

21. Using Multiple Source Images

22. IBR Survey Image-Based Rendering & Modeling Light Field Rendering (or Lumigraph) Stanford/Microsoft 3D Warping (or Plenoptic Modeling) UNC-Chapel Hill

23. Light Field & Lumigraph

24. Images as 4D Samples Consider each image pixel a sample of 4D Light Field.

25. Does it Matter Where We Place the Planes? Yes! Depth correction in Lumigraphs:

26. Concentric Mosaic Hold a camera on a stick, then sweep a circle. Viewpoint is constrained on a 2D plane. Reducing the 4D light field to a 3D subspace.

27. Surface Light Field May be considered a compression scheme for light field data. 3D geometry required.

28. LYTRO Light Field Camera See https://www.lytro.com/science_insidehttps://www.lytro.com/science_inside

29. Further Reading on Light Field See Marc Levoy’s IEEE Computer 2006 article at: http://graphics.stanford.edu/papers/lfph oto/levoy-lfphoto-ieee06.pdf

30. Camera Array Source: http://sabia.tic.udc.es/gc/Contenidos%20adicionales/trabajos/Peliculas/FX/ej3.htmlhttp://sabia.tic.udc.es/gc/Contenidos%20adicionales/trabajos/Peliculas/FX/ej3.html

31. Image-Based Lighting -- Light Stage Take photos under single point light at various positions. Trivial questions: how to produce new images at: –Two point lights? –Area light? –Environment light (captured by light probe)?