Advanced Interactive Image Manipulation

Lecturer:

Tutor:

Supervisor:

Department of Computer Graphics and Interaction

Synopsis:

This course presents a comprehensive overview of modern methods for interactive editing of digital images and video. It mainly deals with practical algorithms that are both easy to implement and have an interesting theoretical basis. Visually attractive applications provide better understanding of basic theoretical background that is also valuable outside the domain of digital image processing.

Requirements:

There are no compulsory prerequisites, however, the course assumes some basic knowledge from previous bachelor and master studies:

A4B01DMA Diskrétní matematika

A0B01LAG Lineární Algebra

A4B01MA2 Matematická analýza

A0B01PSI Pravděpodobnost, statistika a teorie informace

A4B01NUM Numerické metody

A4B33OPT Optimalizace

A4B33ALG Algoritmizace

A0B36PR1 Programování 1

A0B36PR2 Programování 2

A4M33DZO Digitální obraz

A4M33PAL Pokročilá algoritmizace

A4M39APG Algoritmy počítačové grafiky

A4M35KO Kombinatorická optimalizace

A4M33MPV Metody počítačového vidění

A4M39DPG Datové struktury počítačové grafiky

A4M33TZ Teoretické základy vidění, grafiky a interakce

http://dcgi.felk.cvut.cz/~sykorad/a4m39aim

Syllabus of lectures:

1. Introduction to interactive digital image editing (overview, remind of previous knowledge)

2. Bilateral filter (basic method, extensions)

3. Bilateral filter (applications)

4. Geodesic distance (basic method, extensions, applications)

5. Homogeneous partial differential equations (Laplace, Poisson, numerical solution)

6. Homogeneous partial differential equations (applications)

7. Inhomogeneous partial differential equations (Laplace-Beltrami, numerical solution)

8. Inhomogeneous partial differential equations (applications)

9. Interactive image segmentation (advanced techniques based on computation of maximum flow in a graph)

10. Interactive image segmentation (generalization, applications, matting Laplacian)

11. Free-form deformations of image and space (linear methods)

12. Free-form deformations of image and space (non-linear methods)

13. Free-form deformations of image and space (advanced techniques in closed form)

14. Reserved

Syllabus of tutorials:

1. Introduction to assignments

2. Selection of assignments

3. Reading papers

4. Implementation

5. Testing

6. Submission of reports

7. Presentation

Study Objective:

This course will introduce algorithms solving the following practical applications: edge-aware editing, tone mapping, HDR compression, abstraction, gradient domain editing, seamless image stitching and cloning, digital photomontage, color-to-gray conversion, context enhancment, interactive segmentation, colorization, painting, adding depth, alpha matting, as-ridig-as-possible image deformation.

Following theoretical background will be studied: bilateral filter, geodesic distance, partial differential equations and their numerical solution, (bi)harmonic functions, linear and non-linear optimization, solution to large sparse linear system, quadratic programming, computation of maximum flow, complex analysis, conformal mapping.

Study materials:

[1] Agarwala et al.: Interactive digital photomontage, 2004.

[2] Agarwala: Efficient Gradient-Domain Compositing Using Quadtrees, 2007.

[3] An & Pellacini: AppProp: All-Pairs Appearance-Space Edit Propagation, 2008.

[4] Bae et al.: Two-scale Tone Management for Photographic, 2006.

[5] Bai & Sapiro: A Geodesic Framework for Fast Interactive Video Segmentation and Matting, 2007.

[6] Bai et al.: Video SnapCut: Robust Video Object Cutout Using Localized Classifiers, 2009.

[7] Ben-Chen et al.: Variational Harmonic Maps for Space Deformation, 2009.

[8] Bhat et al.: GradientShop: A Gradient-Domain Optimization Framework for Image and Video Filtering, 2009.

[9] Bookstein: Principal Warps: Thin-Plate Splines and the Decomposition of Deformations, 1989.

[10] Boykov & Funka-Lea: Graph Cuts and Efficient N-D Image Segmentation, 2006.

[11] Chen et al.: Real-Time Edge-Aware Image Processing With the Bilateral Grid, 2007.

[12] Criminisi et al.: Geodesic Image and Video Editing, 2011.

[13] Durand et al.: Fast bilateral filtering for the display of high-dynamic-range images, 2002.

[14] Eisemann et al.: Flash photography enhancement via intrinsic relighting, 2004.

[15] Elder & Goldberg: Image Editing in the Contour Domain, 2001.

[16] Farbman et al.: Edge-preserving decompositions for multi-scale tone and detail manipulation, 2008.

[17] Farbman et al.: Coordinates for Instant Image Cloning, 2009.

[18] Fattal et al.: Gradient domain high dynamic range compression, 2002.

[19] Floater: Mean Value Coordinates, 2003.

[20] Gastal & Oliveira: Domain Transform for Edge-Aware Image and Video Processing, 2011.

[21] Grady: Multilabel Random Walker Image Segmentation Using Prior Models, 2005.

[22] Grady & Tasdizen: A Geometric Multigrid Approach to Solving the 2D Inhomogeneous Laplace Equation with Internal Dirichlet Boundary Conditions, 2005.

[23] Grady: Random Walks for Image Segmentation, 2006.

[24] Grady & Sinop: Fast Approximate Random Walker Segmentation Using Eigenvector Precomputation, 2008.

[25] He et al.: Single Image Haze Removal Using Dark Channel Prior, 2009.

[26] Igarashi et al.: As-rigid-as-possible shape manipulation, 2005.

[27] Jacobson et al.: Bounded Biharmonic Weights for Real-Time Deformation, 2011.

[28] Jeschke et al.: A GPU Laplacian Solver for Diffusion Curves and Poisson Image Editing, 2009.

[29] Jia et al.: Drag-and-Drop Pasting, 2006.

[30] Joshi et al.: Harmonic Coordinates for Character Articulation, 2007.

[31] Kass et al.: Smoothed local histogram filters, 2010.

[32] Kopf et al.: Joint Bilateral Upsampling, 2007.

[33] Levin et al.: Colorization using optimization, 2004.

[34] Levin et al.: A Closed Form Solution to Natural Image Matting, 2008.

[35] Levin et al.: Spectral Matting, 2008.

[36] Li et al.: Lazy snapping, 2004.

[37] Lipman et al.: Green Coordinates, 2008.

[38] Lischinski et al.: Interactive Local Adjustment of Tonal Values, 2006.

[39] Liu et al.: Paint Selection, 2009.

[40] McCann & Pollard: Real-time Gradient-domain Painting, 2008.

[41] Muller et al.: Meshless deformations based on shape matching, 2005.

[42] Neumann et al.: An Efficient Perception-based Adaptive Color to Gray Transformation, 2007.

[43] Orzan et al.: Diffusion Curves: A Vector Representation for Smooth-Shaded Images, 2008.

[44] Perez et al.: Poisson image editing, 2003.

[45] Petschnigg et al.: Digital photography with flash and no-flash image pairs, 2004.

[46] Raskar et al.: Image Fusion for Context Enhancement and Video Surrealism, 2004.

[47] Rivers & James: FastLSM: Fast Lattice Shape Matching for Robust Real-Time Deformation, 2007.

[48] Rother et al.: GrabCut: Interactive Foreground Extraction using Iterated Graph Cuts, 2004.

[49] Schaefer et al.: Image Deformation Using Moving Least Squares, 2006.

[50] Singaraju et al.: P-Brush: Continuous Valued MRFs with Normed Pairwise Distributions for Image Segmentation, 2009.

[51] Summa et al.: Interactive Editing of Massive Imagery Made Simple: Turning Atlanta into Atlantis, 2011.

[52] Sumner et al.: Embedded Deformation for Shape Manipulation, 2007.

[53] Sýkora et al.: LazyBrush: Flexible Painting Tool for Hand-drawn Cartoons, 2009.

[54] Sýkora et al.: As-Rigid-As-Possible Image Registration for Hand-drawn Cartoon Animations, 2009.

[55] Sýkora et al.: Adding Depth to Cartoons Using Sparse Depth (In)equalities, 2010.

[56] Sýkora et al.: TexToons: Practical Texture Mapping for Hand-drawn Cartoon Animations, 2011.

[57] Wang et al.: Soft Scissors: An Interactive Tool for Realtime High Quality Matting, 2007.

[58] Weber et al.: Parallel Algorithms for Approximation of Distance Maps on Parametric Surfaces, 2008.

[59] Weber et al.: Complex Barycentric Coordinates with Applications to Image Deformation, 2009.

[60] Weber et al.: Controllable Conformal Maps for Shape Deformation and Interpolation, 2010.

[61] Weiss: Fast Median and Bilateral Filtering, 2006.

[62] Winnemoller et al.: Real-Time Video Abstraction, 2006.

[63] Yatziv et al.: Fast Image and Video Colorization using Chrominance Blending, 2006.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans: