Let us have some after lunch fun. Fast Image and Video Colorization (and beyond) using Chrominance Blending Yatziv and S.

Slides:



Advertisements
Similar presentations
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model Ce Liu Heung-Yeung Shum Chang Shui Zhang CVPR 2001.
Advertisements

Super-Resolution Texturing for Online Virtual Globes
Color to Grayscale Conversion with Chrominance Contrast Yuting Ye Computer Science Department April 27, 2006.
SOFT SCISSORS: AN INTERACTIVE TOOL FOR REALTIME HIGH QUALITY MATTING International Conference on Computer Graphics and Interactive Techniques ACM SIGGRAPH.
Spectral Matting Anat Levin 1,2 Alex Rav-Acha 1 Dani Lischinski 1 1 School of CS&Eng The Hebrew University 2 CSAIL MIT.
1School of CS&Eng The Hebrew University
1 Roey Izkovsky Yuval Kaminka Matting Helping Superman fly since 1978.
Grayscale Image Matting And Colorization Tongbo Chen, Yan Wang, Volker Schillings, Christoph Meinel FB IV-Informatik, University of Trier, Trier 54296,
Color2Gray Imanol Gómez Rubio Computational Photography – 11/Dec/2007 TU-Berlin.
Color2Gray: Salience-Preserving Color Removal
Color2Gray: Salience-Preserving Color Removal Amy Gooch Sven Olsen Jack Tumblin Bruce Gooch Northwestern University.
Color2Gray: Salience-Preserving Color Removal Amy A. Gooch Sven C. Olsen Jack Tumblin Bruce Gooch.
Computing 3D Geometry Directly From Range Images Sarah F. Frisken and Ronald N. Perry Mitsubishi Electric Research Laboratories.
Light Mixture Estimation for Spatially Varying White Balance
Transferring Color to Greyscale Images Tomihisa Welsh, Michael Ashikhmin, Klaus Mueller (Stony Brook University) SIGGRAPH2002.
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 1: Introduction.
Announcements Project 4 questions? Guest lectures Thursday: Richard Ladner “tactile graphics” Next Tuesday: Jenny Yuen and Jeff Bigham.
Digital Cameras CCD (Monochrome) RGB Color Filter Array.
Point Processing : Computational Photography Alexei Efros, CMU, Fall 2011 Some figures from Steve Seitz, and Gonzalez et al.
Natural Video Matting with Depth Jonathan Finger Oliver Wang University of California, Santa Cruz {jfinger,
Transferring Color to Greyscale Images Tomihisa Welsh, Michael Ashikhmin, Klaus Mueller Presented by Steven Scher
A Closed Form Solution to Natural Image Matting
1 Visual Information Extraction in Content-based Image Retrieval System Presented by: Mian Huang Weichuan Dong Apr 29, 2004.
Curve Analogies Aaron Hertzmann Nuria Oliver Brain Curless Steven M. Seitz University of Washington Microsoft Research Thirteenth Eurographics.
Colorization by Example R. Irony, D. Cohen-Or, D. Lischinski Tel-Aviv University The Hebrew University of Jerusalem Eurgraphics Symposium on Rendering.
Chapter 2 Computer Imaging Systems. Content Computer Imaging Systems.
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 10 Image Segmentation Chapter 10 Image Segmentation.
Traffic Sign Recognition Jacob Carlson Sean St. Onge Advisor: Dr. Thomas L. Stewart.
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 2: Digital Image Fundamentals.
Real-Time Ray Tracing 3D Modeling of the Future Marissa Hollingsworth Spring 2009.
Color Transfer in Correlated Color Space Xuezhong Xiao, Computer Science & Engineering Department, Shanghai Jiao Tong University Lizhuang Ma., Computer.
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 6 Color Image Processing Chapter 6 Color Image.
1 Motivation Video Communication over Heterogeneous Networks –Diverse client devices –Various network connection bandwidths Limitations of Scalable Video.
Image Analogies Aaron Hertzmann (1,2) Charles E. Jacobs (2) Nuria Oliver (2) Brian Curless (3) David H. Salesin (2,3) 1 New York University 1 New York.
Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller Center for Visual Computing Stony Brook University.
Ron Yanovich & Guy Peled 1. Contents Grayscale coloring background Luminance / Luminance channel Segmentation Discrete Cosine Transform K-nearest-neighbor.
Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.
Photoshop Software Rasterized, file formats, and printing choices.
 In electrical engineering and computer science image processing is any form of signal processing for which the input is an image, such as a photograph.
Interactive Time-Dependent Tone Mapping Using Programmable Graphics Hardware Nolan GoodnightGreg HumphreysCliff WoolleyRui Wang University of Virginia.
Desktop Video. Basics Desktop Video Desktop Video Frame Rate Frame Rate.
FAST: Fully Autonomous Sentry Turret
Eurographics 2012, Cagliari, Italy 3D Material Style Transfer Chuong H. Nguyen 1, Tobias Ritschel 2, Karol Myszkowski 1, Elmar Eisemann 2, Hans-Peter Seidel.
Specialized Input and Output. Inputting Sound ● The microphone is the most basic device for inputting sounds into a computer ● Microphones capture sounds.
Previous lecture Texture Synthesis Texture Transfer + =
Dense Image Over-segmentation on a GPU Alex Rodionov 4/24/2009.
Tone Mapping on GPUs Cliff Woolley University of Virginia Slides courtesy Nolan Goodnight.
Digital Image Processing, 3rd ed. © 1992–2008 R. C. Gonzalez & R. E. Woods Gonzalez & Woods Chapter 1 Introduction Chapter.
Digital Image Processing
1 Computer Science 631 Multimedia Systems Prof. Ramin Zabih Computer Science Department CORNELL UNIVERSITY.
Palette-based Photo Recoloring
Video Tracking G. Medioni, Q. Yu Edwin Lei Maria Pavlovskaia.
Multimedia Programming 14: Matting Departments of Digital Contents Sang Il Park.
Data-driven Architectural texture mapping Texture mapping Un-textured 3D sceneTextured output Textured Architectures 由于建筑物的3D model和 textures均属于structured.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
CAGD&C G Color Analogies and its applications reporter:Shuangmin Chen.
Image Research Topics. Colors Color2Grey Colorization Color transfer Color harmonization.
1 Section 1.3 Binary Number Systems Fundamentals of Java: AP Computer Science Essentials, 4th Edition Lambert / Osborne.
Rotoscoping Senior Capstone Project | Ted Trisco
Announcements Project 4 out today help session at the end of class.
Geodesics on Implicit Surfaces and Point Clouds
Data-driven methods: Texture 2 (Sz 10.5)
A Computational Darkroom for BW Photography
Direct digital control systems &Software
Implementation on video object segmentation algorithm
Lecture 16 Figures from Gonzalez and Woods, Digital Image Processing, Second Edition, 2002.
Color Image Processing
Gradient Domain Salience-preserving Color-to-gray Conversion
Exam Objectives: Identify Design Elements When Preparing Images
More on natural image matting
Presentation transcript:

Let us have some after lunch fun

Fast Image and Video Colorization (and beyond) using Chrominance Blending Yatziv and S.

Hand-Tinting of Photos 19 th century

Hand-Tinting of postcards early 20 th century

Computer Assisted Colorization Given: a single dimension of luminance Output: three dimensions –Luminance –Chrominance Colorization is ambiguous in nature and requires some amount of human interaction.

Commercial Software Adobe Photoshop Tutorial

Computer Assisted Colorization Interfaces Sample Based –One or more color images as a source –In video, use one or more colored frames sample framegray-scaleresult colored image Example source: Sykora, Burianek, Zara “Colorization of Black-and-White Cartoons”

Computer Assisted Colorization Interfaces Chrominance Scribble Based –Small chrominance markings –Scribble area << image size gray-scalescribblesresult colored image Example source: Levin, Lischinski, Weiss, “Colorization using optimization,” SIGGRAPH’ 04

Previous Work Luminance Keying –Gonzalez, Woods, ‘Digital Image Processing’. –Welsh, Ashikhmin, Mueller, “Transferring color to grayscale images”. –Reinhard, Ashikhmin, Gooch, Shirley, “Color transfer between images”. –Hertzmann, Jacobs, Oliver, Curless, Salesin, “Image analogies”. Segmentation –Chen, Wang, Schillings, Meinel, “Gray-scale matting and colorization”. –Sykora, Burianek, Zara “Colorization of Black-and-White Cartoons”. Geometry Based –Sapiro, “Inpainting the colors”. –Levin, Lischinski, Weiss, “Colorization using optimization”

Our Approach Fast Image and Video Colorization using Chrominance Blending C s,t t s Intrinsic distance: Y is the gray-scale channel c Distance from a chrominance c: d c (t) can be calculated efficiently using improved “Fast Marching” algorithm.

…Our Approach Fast Image and Video Colorization using Chrominance Blending tc1c1 c3c3 c2c2 for (typically B=4) DW Shepard interpolation

Examples

Example - Video

NEAR FAR

DE CO LO RIZI NG

Video Inpainting Patwardhan and S.

Tracking under severe occlusions Bartesaghi and S.