Matting and Transparency 15-463: Computational Photography Alexei Efros, CMU, Fall 2007.

Slides:



Advertisements
Similar presentations
Computer graphics & visualization Global Illumination Effects.
Advertisements

Announcements Project 2 due today Project 3 out today –demo session at the end of class.
3D Modeling from a photograph
Fast Separation of Direct and Global Images Using High Frequency Illumination Shree K. Nayar Gurunandan G. Krishnan Columbia University SIGGRAPH Conference.
Lecture 24: Segmentation CS6670: Computer Vision Noah Snavely From Sandlot ScienceSandlot Science.
Procam and Campro Shree K. Nayar Computer Science Columbia University Support: NSF, ONR Procams 2006 PROCAMS Shree K. Nayar,
--- some recent progress Bo Fu University of Kentucky.
Spherical Convolution in Computer Graphics and Vision Ravi Ramamoorthi Columbia Vision and Graphics Center Columbia University SIAM Imaging Science Conference:
Capturing light Source: A. Efros. Image formation How bright is the image of a scene point?
Measuring BRDFs. Why bother modeling BRDFs? Why not directly measure BRDFs? True knowledge of surface properties Accurate models for graphics.
Computational Photography, Fall 2013
Advanced Computer Graphics CSE 190 [Spring 2015], Lecture 5 Ravi Ramamoorthi
Video Matting from Depth Maps Jonathan Finger Oliver Wang University of California, Santa Cruz {jfinger,
Natural Video Matting using Camera Arrays Neel S. JoshiWojciech MatusikShai Avidan Mitsubishi Electric Research Laboratory University of California, San.
Image Compositing and Matting. Introduction Matting and compositing are important operations in the production of special effects. These techniques enable.
1 Roey Izkovsky Yuval Kaminka Matting Helping Superman fly since 1978.
Rendering with Environment Maps Jaroslav Křivánek, KSVI, MFF UK
1. What is Lighting? 2 Example 1. Find the cubic polynomial or that passes through the four points and satisfies 1.As a photon Metal Insulator.
Illumination Model How to compute color to represent a scene As in taking a photo in real life: – Camera – Lighting – Object Geometry Material Illumination.
Copyright  Pat Hanrahan Optical Printing From: “Special Optical Effects,” Zoran Perisic From: “Industrial Light and Magic,” Thomas Smith (p. 181)
A Signal-Processing Framework for Forward and Inverse Rendering COMS , Lecture 8.
 P Hanrahan & M Levoy “Pulling a Matte” - Matte Creation From digitized images o Blue-screen matting (Petro Vlahos) Separate blue background from foreground.
Measurement, Inverse Rendering COMS , Lecture 4.
Copyright  Pat Hanrahan Composing Two Elements Background ForegroundTraveling Matte Holdout Matte * *+ += =
Natural Video Matting with Depth Jonathan Finger Oliver Wang University of California, Santa Cruz {jfinger,
Background Subtraction and Matting : Computational Photography Alexei Efros, CMU, Fall 2006 © Yuri Bonder.
Light by Ted Adelson Readings Forsyth, Chapters 4, 6 (through 6.2)
Advanced Computer Graphics (Spring 2005) COMS 4162, Lecture 6: Image Compositing, Morphing Ravi Ramamoorthi
Photorealistic Rendering of Rain Streaks Department of Computer Science Columbia University Kshitiz Garg Shree K. Nayar SIGGRAPH Conference July 2006,
Background Subtraction : Rendering and Image Processing Alexei Efros.
Announcements Final project presentations on Wednesday Each group has 10 minutes Place.ppt talk in artifact directory Final reports due on Friday at 11:59pm.
Projection Defocus Analysis for Scene Capture and Image Display Li Zhang Shree Nayar Columbia University IIS SIGGRAPH Conference July 2006, Boston,
Matting and Transparency : Computational Photography Alexei Efros, CMU, Fall 2006.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Image Compositing and Blending : Computational Photography Alexei Efros, CMU, Fall 2007 © NASA.
Environment Matting and Compositing CS 395 – Advanced GraphicsPresented by Jay Hetler Douglas E. Zongker ~ Dawn M. Werner ~ Brian Curless ~ David H. Salsin.
Copyright  Pat Hanrahan Composing Two Elements Background ForegroundTraveling Matte Holdout Matte * *+ += =
Matting : Rendering and Image Processing Alexei Efros …with many slides from Kyros Kutulakos.
Measure, measure, measure: BRDF, BTF, Light Fields Lecture #6
02/14/02(c) University of Wisconsin 2002, CS 559 Last Time Filtering Image size reduction –Take the pixel you need in the output –Map it to the input –Place.
Computer Graphics Inf4/MSc Computer Graphics Lecture Notes #16 Image-Based Lighting.
Light and shading Source: A. Efros.
Selected Topics in Global Illumination Computation Jaroslav Křivánek Charles University, Prague
Image-Based Rendering from a Single Image Kim Sang Hoon Samuel Boivin – Andre Gagalowicz INRIA.
-Global Illumination Techniques
Ray Tracing Sang Il Park SEjong University With lots of slides stolen from Jehee Lee, Doug James, Steve Seitz, Shree Nayar, Alexei Efros, Fredo Durand.
Image-based rendering Michael F. Cohen Microsoft Research.
Filtering and Color To filter a color image, simply filter each of R,G and B separately Re-scaling and truncating are more difficult to implement: –Adjusting.
Capturing light Source: A. Efros.
Digital Image Compositing. Compositing for volume rendering c1 c2 c3 The initial pixel color = Black opaque Back-to-Front compositing: use ‘under’ operator.
Image-Based Rendering of Diffuse, Specular and Glossy Surfaces from a Single Image Samuel Boivin and André Gagalowicz MIRAGES Project.
Interreflections : The Inverse Problem Lecture #12 Thanks to Shree Nayar, Seitz et al, Levoy et al, David Kriegman.
Photo-realistic Rendering and Global Illumination in Computer Graphics Spring 2012 Material Representation K. H. Ko School of Mechatronics Gwangju Institute.
On robust Monte Carlo algorithms for multi-pass global illumination Frank Suykens – De Laet 17 September 2002.
Visual Appearance Chapter 4 Tomas Akenine-Möller Department of Computer Engineering Chalmers University of Technology.
Multimedia Programming 14: Matting Departments of Digital Contents Sang Il Park.
COMPUTER GRAPHICS CS 482 – FALL 2015 OCTOBER 6, 2015 IMAGE MANIPULATION COMPRESSION COMPOSITING.
Illumination Model How to compute color to represent a scene As in taking a photo in real life: – Camera – Lighting – Object Geometry Material Illumination.
Matting and Transparency : Computational Photography Alexei Efros, CMU, Spring 2010.
Che-An Wu Background substitution. Background Substitution AlphaMa p Trimap Depth Map Extract the foreground object and put into another background Objective.
Image-based Lighting Computational Photography
Advanced Computer Graphics
Merle Norman Cosmetics, Los Angeles
Composing Two Elements
(c) 2002 University of Wisconsin
Lighting.
Matting, Transparency, and Illumination
Illumination Model How to compute color to represent a scene
(c) 2002 University of Wisconsin
Camera Culture Camera Culture Ramesh Raskar Ramesh Raskar
Presentation transcript:

Matting and Transparency : Computational Photography Alexei Efros, CMU, Fall 2007

How does Superman fly? Super-human powers? OR Image Matting?

“Pulling a Matte” Problem Definition: The separation of an image C into –A foreground object image C o, –a background image C b, –and an alpha matte  C o and  can then be used to composite the foreground object into a different image Hard problem Even if alpha is binary, this is hard to do automatically (background subtraction problem) For movies/TV, manual segmentation of each frame is infeasible Need to make a simplifying assumption…

Average/Median Image What can we do with this?

Background Subtraction - =

Crowd Synthesis (with Pooja Nath) 1.Do background subtraction in each frame 2.Find and record “blobs” 3.For synthesis, randomly sample the blobs, taking care not to overlap them

Background Subtraction A largely unsolved problem… Estimated background Difference Image Thresholded Foreground on blue One video frame

Blue Screen

Blue Screen matting Most common form of matting in TV studios & movies Petros Vlahos invented blue screen matting in the 50s. His Ultimatte ® is still the most popular equipment. He won an Oscar for lifetime achievement. A form of background subtraction: Need a known background Compute alpha as SSD(C,Cb) > threshold –Or use Vlahos’ formula:  = 1-p 1 (B-p 2 G) Hope that foreground object doesn’t look like background –no blue ties! Why blue? Why uniform?

The Ultimatte p 1 and p 2

Blue screen for superman?

Semi-transparent mattes What we really want is to obtain a true alpha matte, which involves semi-transparency Alpha between 0 and 1

Review: two issues Semi-transparent objects Pixels too large

Review: alpha channel Add one more channel: Image(R,G,B,alpha) Sprite! Encodes transparency (or pixel coverage): Alpha = 1:opaque object (complete coverage) Alpha = 0:transparent object (no coverage) 0<Alpha<1:semi-transparent (partial coverage) Example: alpha = 0.7 Partial coverage or semi-transparency

Matting Problem: Mathematical Definition

Why is general matting hard?

Solution #1: No Blue!

Solution #2: Gray or Flesh

Triangulation Matting (Smith & Blinn) How many equations? How many unknowns? Does the background need to be constant color?

The Algorithm

Triangulation Matting Examples

More Examples

More examples

Problems with Matting Images do not look realistic Lack of Refracted Light Lack of Reflected Light Solution: Modify the Matting Equation

Environment Matting and Compositing slides by Jay Hetler Douglas E. Zongker ~ Dawn M. Werner ~ Brian Curless ~ David H. Salsin

Environment Matting Equation C = F + (1-  )B +  C ~ Color F ~ Foreground color B ~ Background color  ~ Amount of light that passes through the foreground  ~ Contribution of light from Environment that travels through the object

Explanation of  R – reflectance image T – Texture image

Environment Mattes

Performance Calibration Matting: minutes extraction time for each texture map (Pentium II 400Mhz) Compositing: 4-40 frames per second Real-Time?

How much better is Environment Matting? Alpha Matte Environment Matte Photograph

How much better is Environment Matting? Alpha Matte Environment Matte Photograph

Movies!

Fast Separation of Direct and Global Images Using High Frequency Illumination Shree K. Nayar Gurunandan G. Krishnan Columbia University SIGGRAPH Conference Boston, July 2006 Support: ONR, NSF, MERL Michael D. Grossberg City College of New York Ramesh Raskar MERL

source surface P Direct and Global Illumination A A : Direct B B : Interrelection C C : Subsurface D participating medium D : Volumetric translucent surface E E : Diffusion camera

direct global radiance Direct and Global Components: Interreflections surface i camera source j BRDF and geometry

High Frequency Illumination Pattern surface camera source fraction of activated source elements + i

High Frequency Illumination Pattern surface fraction of activated source elements camera source + - i

Separation from Two Images directglobal

Other Global Effects: Subsurface Scattering translucent surface camera source i j

Other Global Effects: Volumetric Scattering surface camera source participating medium i j

Diffuse Interreflections Specular Interreflections Volumetric Scattering Subsurface Scattering Diffusion

Scene

DirectGlobal

Real World Examples: Can You Guess the Images?

Eggs: Diffuse Interreflections DirectGlobal

Wooden Blocks: Specular Interreflections DirectGlobal

Kitchen Sink: Volumetric Scattering Volumetric Scattering: Chandrasekar 50, Ishimaru 78 DirectGlobal

Peppers: Subsurface Scattering DirectGlobal

Hand DirectGlobal Skin: Hanrahan and Krueger 93, Uchida 96, Haro 01, Jensen et al. 01, Cula and Dana 02, Igarashi et al. 05, Weyrich et al. 05

Face: Without and With Makeup GlobalDirect GlobalDirect Without Makeup With Makeup

Blonde Hair Hair Scattering: Stamm et al. 77, Bustard and Smith 91, Lu et al. 00 Marschner et al. 03 DirectGlobal