Near-Regular Texture Analysis and Manipulation Written by: Yanxi Liu Yanxi Liu Wen-Chieh Lin Wen-Chieh Lin James Hays James Hays Presented by: Alex Hadas.

Slides:



Advertisements
Similar presentations
Texture Symmetry A lecture by Alexey Burshtein. Definitions Regular texture is a periodic pattern containing translation symmetry and (possibly) rotation,
Advertisements

Image Quilting and Apples
Andrew Nealen and Marc Alexa, Discrete Geometric Modeling Group, TU Darmstadt, 2004 Fast and High Quality Overlap Repair for Patch-Based Texture Synthesis.
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Data-driven methods: Texture (Sz 10.5) Cs129 Computational Photography James Hays, Brown, Spring 2011 Many slides from Alexei Efros.
Texture Synthesis on [Arbitrary Manifold] Surfaces Presented by: Sam Z. Glassenberg* * Several slides borrowed from Wei/Levoy presentation.
Procedural Content Tiling
Kernel-based tracking and video patch replacement Igor Guskov
Chapter 6 Feature-based alignment Advanced Computer Vision.
Lapped Textures Emil Praun and Adam Finkelstien (Princeton University) Huges Hoppe (Microsoft Research) SIGGRAPH 2000 Presented by Anteneh.
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
Maryia Kazakevich “Texture Synthesis by Patch-Based Sampling” Texture Synthesis by Patch-Based Sampling Real-Time Texture Synthesis By Patch-Based Sampling,
Lapped Textures Emil Praun Adam Finkelstein Hugues Hoppe Emil Praun Adam Finkelstein Hugues Hoppe Princeton University Microsoft Research Princeton University.
Image Quilting for Texture Synthesis & Transfer Alexei Efros (UC Berkeley) Bill Freeman (MERL) +=
Overview of Texture Synthesis Ganesh Ramanarayanan Cornell Graphics Seminar.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Texture Splicing Yiming Liu, Jiaping Wang, Su Xue, Xin Tong, Sing Bing Kang, Baining Guo.
Detecting Image Region Duplication Using SIFT Features March 16, ICASSP 2010 Dallas, TX Xunyu Pan and Siwei Lyu Computer Science Department University.
Texture Synthesis on Surfaces Paper by Greg Turk Presentation by Jon Super.
Image Morphing : Computational Photography Alexei Efros, CMU, Fall 2005 © Alexey Tikhonov.
Image Morphing, Triangulation CSE399b, Spring 07 Computer Vision.
Statistical Color Models (SCM) Kyungnam Kim. Contents Introduction Trivariate Gaussian model Chromaticity models –Fixed planar chromaticity models –Zhu.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
SIGGRAPH 2003 Jingdan Zhang, Kun Zhou, Luiz Velho, Baining Guo, Heung-Yeung Shum.
Image Morphing CSC320: Introduction to Visual Computing
What Does the Scene Look Like From a Scene Point? Donald Tanguay August 7, 2002 M. Irani, T. Hassner, and P. Anandan ECCV 2002.
1 Texture. 2 Overview Introduction Painted textures Bump mapping Environment mapping Three-dimensional textures Functional textures Antialiasing textures.
Generating panorama using translational movement model.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
Light Using Texture Synthesis for Non-Photorealistic Shading from Paint Samples. Christopher D. Kulla, James D. Tucek, Reynold J. Bailey, Cindy M. Grimm.
COLLEGE OF ENGINEERING UNIVERSITY OF PORTO COMPUTER GRAPHICS AND INTERFACES / GRAPHICS SYSTEMS JGB / AAS 1 Shading (Shading) & Smooth Shading Graphics.
09/09/03CS679 - Fall Copyright Univ. of Wisconsin Last Time Event management Lag Group assignment has happened, like it or not.
Terrain Synthesis by Digital Elevation Models Howard Zhou, Jie Sun, Greg Turk, and James M. Rehg
ME 6501 Computer Aided Design
Geometric Camera Models
Course 9 Texture. Definition: Texture is repeating patterns of local variations in image intensity, which is too fine to be distinguished. Texture evokes.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros (UC Berkeley) William T. Freeman (MERL) Siggraph01 ’
The Quotient Image: Class-based Recognition and Synthesis Under Varying Illumination T. Riklin-Raviv and A. Shashua Institute of Computer Science Hebrew.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
TextureAmendment Reducing Texture Distortion in Constrained Parameterizations Yu-Wing TaiNational University of Singapore Michael S. BrownNational University.
2D Texture Synthesis Instructor: Yizhou Yu. Texture synthesis Goal: increase texture resolution yet keep local texture variation.
Graphcut Textures Image and Video Synthesis Using Graph Cuts
Two Patch-based Algorithms for By-example Texture Synthesis Bruno Galerne MAP5, Université Paris Descartes 1 Master 2 Traitement.
Krivljenje slike - warping. Princip 2D krivljenja Demo.
1Ellen L. Walker 3D Vision Why? The world is 3D Not all useful information is readily available in 2D Why so hard? “Inverse problem”: one image = many.
Point Distribution Models Active Appearance Models Compilation based on: Dhruv Batra ECE CMU Tim Cootes Machester.
Texture Synthesis by Image Quilting CS766 Class Project Fall 2004 Eric Robinson.
Multimedia Programming 10: Image Morphing
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
Robotics Chapter 6 – Machine Vision Dr. Amit Goradia.
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Eigen Texture Method : Appearance compression based method Surface Light Fields for 3D photography Presented by Youngihn Kho.
SIGGRAPH 2007 Hui Fang and John C. Hart.  We propose an image editing system ◦ Preserve its detail and orientation by resynthesizing texture from the.
Color Image Segmentation Mentor : Dr. Rajeev Srivastava Students: Achit Kumar Ojha Aseem Kumar Akshay Tyagi.
Hebrew University Image Processing Exercise Class 8 Panoramas – Stitching and Blending Min-Cut Stitching Many slides from Alexei Efros.
Deformation Modeling for Robust 3D Face Matching Xioguang Lu and Anil K. Jain Dept. of Computer Science & Engineering Michigan State University.
Two Patch-based Algorithms for By-example Texture Synthesis
A Plane-Based Approach to Mondrian Stereo Matching
Graphcut Textures:Image and Video Synthesis Using Graph Cuts
Image Morphing © Zooface Many slides from Alexei Efros, Berkeley.
Detail Preserving Shape Deformation in Image Editing
Representing Moving Images with Layers
Representing Moving Images with Layers
Brief Review of Recognition + Context
Image Quilting for Texture Synthesis & Transfer
Outline Texture modeling - continued Julesz ensemble.
Presentation transcript:

Near-Regular Texture Analysis and Manipulation Written by: Yanxi Liu Yanxi Liu Wen-Chieh Lin Wen-Chieh Lin James Hays James Hays Presented by: Alex Hadas Alex Hadas

What we will see today? Regular, Near-Regular Texture Definition Regular, Near-Regular Texture Definition Previous Approaches Previous Approaches Near-Regular Texture Analysis Near-Regular Texture Analysis Regularity Measurements Regularity Measurements Near-Regular Texture Manipulation Near-Regular Texture Manipulation Near-Regular Texture Synthesis Algorithm Near-Regular Texture Synthesis Algorithm

Regular, Near-Regular Texture Definition Regular Texture – wallpaper-like, congruent 2D tiling whose structural regularity can be completely characterized by 17 wallpaper groups Regular Texture – wallpaper-like, congruent 2D tiling whose structural regularity can be completely characterized by 17 wallpaper groups Example A: Cloth, Cloth, Tahiti TahitiTahiti Example taken from Wikipedia Wikipedia

Regular, Near-Regular Texture Definition Underlying lattice structure can be represented and generated by a pair of linear independent translations Underlying lattice structure can be represented and generated by a pair of linear independent translations Example C: Painted porcelain, porcelain China Example taken from Wikipedia Wikipedia T1T1 T2T2

Regular, Near-Regular Texture Definition The smallest bounded region that produces (under translation subgroup) simultaneously a covering (no gaps) and a packing (no overlaps) of the texture pattern on 2D plane is called a tile. The smallest bounded region that produces (under translation subgroup) simultaneously a covering (no gaps) and a packing (no overlaps) of the texture pattern on 2D plane is called a tile. Example B: Ornamental painting, NinevehNineveh, Assyria Assyria NinevehAssyria Example taken From Wikipedia Wikipedia

Regular, Near-Regular Texture Definition To Algorithm To Algorithm

Regular, Near-Regular Texture Definition Near-Regular Texture is statistical distortion of a regular, wallpaper like congruent tiling, possibly with individual variations in tile shape, size, color and lighting Near-Regular Texture is statistical distortion of a regular, wallpaper like congruent tiling, possibly with individual variations in tile shape, size, color and lighting

Regular, Near-Regular Texture Definition A Near – Regular Texture p = d(p r ), where A Near – Regular Texture p = d(p r ), where  p r is regular texture,  d = d geo ×d light ×d color, where d geo – Geometric Transformation d geo – Geometric Transformation d light – Lighting Changes d light – Lighting Changes d color – Color Alterations d color – Color Alterations

Regular, Near-Regular Texture Definition Examples of Near-Regular Textures Examples of Near-Regular Textures Brick wall Snake Cloth

Regular, Near-Regular Texture Definition Categorization of Near – Regular Textures (NRT) Type G eometry C olor SymbolsExample 0 R egular GRCR I Irregular GRCI II R egular GICR III Irregular GICI

Regular Texture

Near - Regular Texture Type I (GRCI)

Near - Regular Texture Type II (GICR)

Near – Regular Texture Type III (GICI)

Previous Approaches Generative model approach Generative model approach –Cost of model-specific parameter tuning

Previous Approaches Sample based approach Sample based approach –Neighborhood-based statistical analysis –Non-parametric estimation Tiling based approach Tiling based approach –Only Type I (Lui [2004b] –Only local boundaries preserved, but global near-regularity not addressed (Cohen et al.[2003]

Previous Approaches –Producing regular patterns with translational symmetry by generating tiling boundaries from closed planar contour Escherization [2000] Input Synthesized results Type I Kwatra et al. 2003

Previous Approaches Texture transfer problem Texture transfer problem –Image Analogies [Hertzmann et al. 2001] –Texture Quilting [Efros and Freeman 2001] Input Synthesized results Type II Efros and Freeman 2001

Previous Approaches Texture replacement on plane Texture replacement on plane –Surface is planar, texture is of type I (Tsin et al. [2001] Separation illuminance and texture using a non-linear filtering technique (Oh et al[2001] Separation illuminance and texture using a non-linear filtering technique (Oh et al[2001]

Near-Regular Texture Analysis Geometric Deformation Field Geometric Deformation Field Lighting Deformation Field Lighting Deformation Field Color Deformation Field Color Deformation Field A Pair of Regularity Measurements A Pair of Regularity Measurements

Geometric Deformation Field computer builds 2D lattice computer builds 2D lattice User adjusts misplaced points User adjusts misplaced points Computer finds optimized lattice Computer finds optimized lattice Using MFFD for capturing 1 to 1 warping field Using MFFD for capturing 1 to 1 warping field Represent warping field in HSV space Represent warping field in HSV space

Geometric Deformation Field t1t1t1t1 t2t2t2t2 t 1 +t 2 t2t2t2t2 t1t1t1t1 t 1 -t 2 t2t2t2t2 t1t1t1t1

NRT Analysis: Geometric Deformation Field Represent warping field in HSV space Represent warping field in HSV space dx dy Color scheme used Displacement Map

Lighting Deformation Field Straighten the NRT lattice using d geo Straighten the NRT lattice using d geo Apply Tsin et al.[2001]’s algorithm for lighting map extraction in the plain Apply Tsin et al.[2001]’s algorithm for lighting map extraction in the plain Apply inverse geometric field Apply inverse geometric field

Lighting Deformation Field

Color Deformation Field PCA method: create set of basis and coefficients PCA method: create set of basis and coefficients

Regularity Measurements Geometric Regularity Geometric Regularity Appearance Regularity Appearance Regularity

Regularity Measurements

Near-Regular Texture Manipulation Geometry Deformation Field Manipulation Geometry Deformation Field Manipulation Texture Replacement Texture Replacement Deformation Field Analogy Deformation Field Analogy Texture Regularity Manipulation Texture Regularity Manipulation

Geometry Deformation Field Manipulation

Results Comparison

Texture Replacement

Deformation Field Analogy AA’ B B’ : : Geometric Deformation Field Lighting Deformation Field Extracted from Input Texture Synthesized from A Result of Deformation Field Analogy

Texture Replacement

NRT Synthesis Algorithm Type I NRT only Type I NRT only What is Tile? What is Tile? What is Tile? What is Tile?

NRT Synthesis Algorithm Minimum tiles set {t i } Minimum tiles set {t i } Maximum tiles set {T i } Maximum tiles set {T i } Centered on half way shifted lattice points Centered on half way shifted lattice points

NRT Synthesis Algorithm Stage 1(analysis) Stage 1(analysis) –Determine from a given sample pattern –Determine lattice anchor points {t i } (user controlled) –For each t i construct maximum tile sets T (centered on lattice points) and T h (centered half way)

NRT Synthesis Algorithm Stage 2 (synthesis) Stage 2 (synthesis) 1)Start from top left corner with random tile chosen from T 2)Add tile to the synthesized texture in a scan line along with step When we reach right boundary place tile in direction with step from left most tile in a row

NRT Synthesis Algorithm Stage 2 (synthesis) (cont.) Stage 2 (synthesis) (cont.) 3)At each lattice or half-way lattice point select T or T h tile set and pick one of the best tiles. Error function value is less that threshold

NRT Synthesis Algorithm Error Function Distance Function Red values of the pixel Blue values of the pixel Green values of the pixel

NRT Synthesis Algorithm Stage 2 (synthesis) (cont.) Stage 2 (synthesis) (cont.) 4)Register selected candidate tile using a correlation-based method 5)Use dynamic programming to “stitch” the overlapping tiles. Apply it separately to horizontal and vertical directions

NRT Synthesis Algorithm Stage 2 (synthesis) (cont.) Stage 2 (synthesis) (cont.) 6)When pasting a tile to existing image apply blending where dynamic programming may have conflicting decisions. 7)Repeat steps 2-6 until the whole image is synthesized

NRT Synthesis Algorithm selected tile depends on distance of pixel to the boundary synthesized tile

NRT Synthesis Algorithm

Limitations Self occlusions Self occlusions Shadows caused by surface geometry Shadows caused by surface geometry Tiles are geometrically aligned Tiles are geometrically aligned

Summary User friendly (lattice definition, lighting map extraction) User friendly (lattice definition, lighting map extraction) Fast (1-20 min lattice adjustment, <1 min DF synthesis) Fast (1-20 min lattice adjustment, <1 min DF synthesis) Simple (MFFD control points number ~ tiles number) Simple (MFFD control points number ~ tiles number)

References Deformable Texture: The Irregular – Regular – Irregular Cycle (Yanxi Lui and Wen-Cheh Lin) Deformable Texture: The Irregular – Regular – Irregular Cycle (Yanxi Lui and Wen-Cheh Lin) Near-Regular Texture Analysis and Manipulation (Yanxi Lui,Wen-Cheh Lin, James Hays) Near-Regular Texture Analysis and Manipulation (Yanxi Lui,Wen-Cheh Lin, James Hays) Promise and Perils of Near-regular Texture(Yanxi Lui and Wen-Cheh Lin,Yanghai Tsin) Promise and Perils of Near-regular Texture(Yanxi Lui and Wen-Cheh Lin,Yanghai Tsin)