Download presentation
Presentation is loading. Please wait.
1
CS 395/495-25: Spring 2003 IBMR: Week 10A Dimensionality of IBMR Methods Jack Tumblin jet@cs.northwestern.edu
2
Reminders ProjA graded: Good Job! 90,95, 110ProjA graded: Good Job! 90,95, 110 ProjB graded: Good! minor H confusions.ProjB graded: Good! minor H confusions. MidTerm graded: novel solutions encouraged.MidTerm graded: novel solutions encouraged. ProjC due Friday, May 16: graded.ProjC due Friday, May 16: graded. ProjD posted, due Friday May 30 too many unfinished—final is coming!ProjD posted, due Friday May 30 too many unfinished—final is coming! Take-Home Final Exam: Assign on Thurs June 5, due June 11Take-Home Final Exam: Assign on Thurs June 5, due June 11
3
Handouts today: Levoy/Marschner BibliographyLevoy/Marschner Bibliography Masselus et. al, 2003: Relighting with 4D incident Light Fields (on the website)Masselus et. al, 2003: Relighting with 4D incident Light Fields (on the website)on the websiteon the website
4
‘Rendering’ from a camera? Many choices of dimensions for IBMR: Shape,Position,Movement, BRDF,Texture,Scattering EmittedLight Reflected,Scattered, Light … ycycycyc zczczczc xcxcxcxc Camera
5
1-D? Moving Line-scan Cameras Multiple-Center-of-Projection Images Rademacher, Pl, Bishop, G., SIGGRAPH '98
6
1-D? Moving Line-scan Cameras Rademacher, Pl, Bishop, G., Multiple-Center-of-Projection Images SIGGRAPH '98.
7
1-D? Moving Line-scan Cameras Shum, Concentric Image Mosaics SIGGRAPH Andrew Davidhazy, RIT : http://www.rit.edu/~andpph/Andrew Davidhazy, RIT : http://www.rit.edu/~andpph/ http://www.rit.edu/~andpph/
8
1-D? Moving Line-scan Cameras ? What other unusual mappings of position vs. 4-D ray direction might help in IBMR? –Example: [Alison Ortony] torus map: --pre-aligned epipolar geometry, --no ‘north/south’ pole problems
9
2-D: Image-Space Manipulations MorphsMorphs –Beier92, –Seitz96, –LightField Morphs 2002... deep pixelsdeep pixels – PTMs, –Environment Matte...
10
Impostors/Billboards:
11
Malzbender, HPlabs 2001 A Mostly 2-D Method Polynomial Texture Maps Store just 6 coefficients at each pixel, get Interactive re-lighting...
12
‘2.5’-D: Images + a little more... 2.5D: Depth textures2.5D: Depth textures Billboards/Impostors, LDIs: Multiple pixels along line-of sight... Jonathan Shade, Steven J. Gortler, Li-wei He, Richard Szeliski. SIGGRAPH 98. http://grail.cs.washington.edu/projects/ldi/ Generalization: LDI Trees, SIGG99 http://www.cs.unc.edu/~ibr/pubs/chang-sg99/abstract.htmlBillboards/Impostors, LDIs: Multiple pixels along line-of sight... Jonathan Shade, Steven J. Gortler, Li-wei He, Richard Szeliski. SIGGRAPH 98. http://grail.cs.washington.edu/projects/ldi/ Generalization: LDI Trees, SIGG99 http://www.cs.unc.edu/~ibr/pubs/chang-sg99/abstract.html http://grail.cs.washington.edu/projects/ldi/http://www.cs.unc.edu/~ibr/pubs/chang-sg99/abstract.html http://grail.cs.washington.edu/projects/ldi/http://www.cs.unc.edu/~ibr/pubs/chang-sg99/abstract.html
13
‘2.5’-D: Images + a little more...
14
2.5D: Images plus different lighting Relighting by linear image combos: demo http://www.sgi.com/grafica/synth/index.htmlRelighting by linear image combos: demo http://www.sgi.com/grafica/synth/index.html http://www.sgi.com/grafica/synth/index.html Non-Physical Combinations:Non-Physical Combinations: –Negative Light –Generalizations—Malzbender2001 and others, –Debevec: sphere of point sources polarizer separates diffuse, specular terms (simplified BRDF) – Factor images for BRDF samples: McCool, Ramamoorthy
15
Debevec ‘Light Stage’
16
Image-Based Actual Re-lighting Film the background in Milan, Measure incoming light, Light the actress in Los Angeles Matte the background Matched LA and Milan lighting. Debevec et al., SIGG2001
17
Williams 1998: ‘Inflated Silhouettes’ http://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessionshttp://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessionshttp://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessions
18
Williams 1998: ‘Inflated Silhouettes’ Symmetric, ‘Natural’ objectsSymmetric, ‘Natural’ objects Reliable Silhouette extractionReliable Silhouette extraction Implicit Function for Depth: rounded, diffused, relaxation...Implicit Function for Depth: rounded, diffused, relaxation... Refine with ? texture/shading?Refine with ? texture/shading? manual ‘paintbox’ for depth?manual ‘paintbox’ for depth? Simple, quick, fairly good results...Simple, quick, fairly good results...
19
Williams 1998: ‘Inflated Silhouettes’ http://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessionshttp://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessionshttp://graphics.stanford.edu/workshops/ibr98/#Schedule%20of%20sessions Not bad! Can we do better?
20
3-D Methods Fans, silhouettes:Fans, silhouettes: –Ramesh Raskar and Michael Cohen. Image Precision Silhouette Edges. I3D 99. Image Precision Silhouette Edges.Image Precision Silhouette Edges. Voxel Carving (Seitz, others)Voxel Carving (Seitz, others) Seitz,1998
21
3D: Try image + other dimensions Halle: Multiple Viewpoint Rendering (SIGG98) http://web.media.mit.edu/~halazar/sig98/halle98.pdfHalle: Multiple Viewpoint Rendering (SIGG98) http://web.media.mit.edu/~halazar/sig98/halle98.pdf http://web.media.mit.edu/~halazar/sig98/halle98.pdf
22
Oh et. al, 2001: 2D 3D 3D ‘Power tools’ for editing 2D images http://graphics.lcs.mit.edu/ibedit/ibedit_s2001_cameraReady.pdf3D ‘Power tools’ for editing 2D images http://graphics.lcs.mit.edu/ibedit/ibedit_s2001_cameraReady.pdf http://graphics.lcs.mit.edu/ibedit/ibedit_s2001_cameraReady.pdf
23
4-D Methods Incoming Rays: 4D Outgoing Rays: 4D Light fieldsLight fields Illum FieldsIllum Fields Shape/Light field refinementShape/Light field refinement
24
4D Methods Light-source Light Fields Accurate Light Source Acquisition and Rendering M. Goesele, X. Granier, W. Heidrich, H.-P. Seidel, SIGG2003
25
Image-Based Synthetic Re-lighting Masselus et al., 2002
26
Basis images Illuminant direction estimation Take pictures and move hand-held light source Incident light map Create weighted sum … · W 1 + · W 2 + + · W n Relit object Masselus et al., 2002, “Free-Form Light Stage”
27
Matusik 2002 Image-Based Shape Approximation
28
Matusik 2002 Image-Based Shape Approximation
29
Rushmeier, 2001 Fine geometric Details Fine Texture/Normal Details Image-Based Shape Refinement
30
5-D Methods and beyond... surface light fields, (Chen et al, SIGG02) Synthetic+ real
31
5-D Methods and beyond... Relighting with 4D Incident Light Fields Vincent Masselus, Pieter Peers, Philip Dutre and Yves D. Willems SIGG2003
32
Rushmeier, 1996Interreflections?
33
END
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.