Texture Splicing Yiming Liu, Jiaping Wang, Su Xue, Xin Tong, Sing Bing Kang, Baining Guo.

Slides:



Advertisements
Similar presentations
Shape Matching and Object Recognition using Low Distortion Correspondence Alexander C. Berg, Tamara L. Berg, Jitendra Malik U.C. Berkeley.
Advertisements

Inverse Texture Synthesis
Jiaping Wang1, Shuang Zhao2, Xin Tong1 John Snyder3, Baining Guo1
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model Ce Liu Heung-Yeung Shum Chang Shui Zhang CVPR 2001.
Pattern-based Texture Metamorphosis Z. Liu, C. Liu, and H. Shum Microsoft Research Asia Y. Yu UIUC.
Data-driven methods: Texture (Sz 10.5) Cs129 Computational Photography James Hays, Brown, Spring 2011 Many slides from Alexei Efros.
Cloth Report by LIANG Cheng. Background Cloth Garment Pattern YarnFiber.
I Images as graphs Fully-connected graph – node for every pixel – link between every pair of pixels, p,q – similarity w ij for each link j w ij c Source:
Recap from Monday Fourier transform analytical tool computational shortcut.
Procedural Content Tiling
Lvdi Wang Tsinghua University Microsoft Research Asia Lvdi Wang Tsinghua University Microsoft Research Asia Kun Zhou Zhejiang University Kun Zhou Zhejiang.
The University of Ontario CS 4487/9687 Algorithms for Image Analysis Multi-Label Image Analysis Problems.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
GrabCut Interactive Image (and Stereo) Segmentation Carsten Rother Vladimir Kolmogorov Andrew Blake Antonio Criminisi Geoffrey Cross [based on Siggraph.
GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.
Graph-Based Image Segmentation
Forward-Backward Correlation for Template-Based Tracking Xiao Wang ECE Dept. Clemson University.
Stephen J. Guy 1. Photomontage Photomontage GrabCut – Interactive Foreground Extraction 1.
Lapped Textures Emil Praun and Adam Finkelstien (Princeton University) Huges Hoppe (Microsoft Research) SIGGRAPH 2000 Presented by Anteneh.
Texture Synthesis Tiantian Liu. Definition Texture – Texture refers to the properties held and sensations caused by the external surface of objects received.
Manifold Bootstrapping for SVBRDF Capture
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.
High-Quality Video View Interpolation
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Texture Synthesis from Multiple Sources Li-Yi Wei Stanford University (was) NVIDIA Corporation (now)
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.
MULTIPLE MOVING OBJECTS TRACKING FOR VIDEO SURVEILLANCE SYSTEMS.
Opportunities of Scale, Part 2 Computer Vision James Hays, Brown Many slides from James Hays, Alyosha Efros, and Derek Hoiem Graphic from Antonio Torralba.
Image Segmentation Rob Atlas Nick Bridle Evan Radkoff.
Junjun Pan 1, Xiaosong Yang 1, Xin Xie 1, Philip Willis 2, Jian J Zhang 1
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Context-based Surface Completion Andrei Sharf, Marc Alexa, Daniel Cohen-Or.
Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.
SIGGRAPH Asia 2011 Preview Seminar - Material Editing - Yoshihiro Kanamori 2011 Nov. 25.
CS774. Markov Random Field : Theory and Application Lecture 13 Kyomin Jung KAIST Oct
Chapter 14: SEGMENTATION BY CLUSTERING 1. 2 Outline Introduction Human Vision & Gestalt Properties Applications – Background Subtraction – Shot Boundary.
Image-based Plant Modeling Zeng Lanling Mar 19, 2008.
Terrain Synthesis by Digital Elevation Models Howard Zhou, Jie Sun, Greg Turk, and James M. Rehg
Image-based rendering Michael F. Cohen Microsoft Research.
Texture Optimization for Example-based Synthesis Vivek Kwatra Irfan Essa Aaron Bobick Nipun Kwatra.
CS 4487/6587 Algorithms for Image Analysis
Data Extraction using Image Similarity CIS 601 Image Processing Ajay Kumar Yadav.
Synthesis of Compact Textures for real-time Terrain Rendering Nader Salman 22 juin 2007 Encadrant : Sylvain Lefebvre.
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.
Geometry Synthesis Ares Lagae Olivier Dumont Philip Dutré Department of Computer Science Katholieke Universiteit Leuven 10 August, 2004.
CS654: Digital Image Analysis Lecture 28: Advanced topics in Image Segmentation Image courtesy: IEEE, IJCV.
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.
Midterm Review. Tuesday, November 3 7:15 – 9:15 p.m. in room 113 Psychology Closed book One 8.5” x 11” sheet of notes on both sides allowed Bring a calculator.
SIGGRAPH 2007 Hui Fang and John C. Hart.  We propose an image editing system ◦ Preserve its detail and orientation by resynthesizing texture from the.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Texture Analysis and Synthesis. Texture Texture: pattern that “looks the same” at all locationsTexture: pattern that “looks the same” at all locations.
Cutting Images: Graphs and Boundary Finding Computational Photography Derek Hoiem, University of Illinois 09/20/12 “The Double Secret”, Magritte.
A 2D/3D correspondence building method for reconstruction of a 3D bone surface model Longwei Fang
Graphcut Textures:Image and Video Synthesis Using Graph Cuts
Summary of “Efficient Deep Learning for Stereo Matching”
Mesh Modelling With Curve Analogies
Announcements Project 4 out today help session at the end of class.
Detail Preserving Shape Deformation in Image Editing
Image Primitives and Correspondence
Paper Presentation: Shape and Matching
Jianping Fan Dept of CS UNC-Charlotte
A Computational Darkroom for BW Photography
Lecture 31: Graph-Based Image Segmentation
Image Quilting for Texture Synthesis & Transfer
Computer Vision Stereo Vision.
Presentation transcript:

Texture Splicing Yiming Liu, Jiaping Wang, Su Xue, Xin Tong, Sing Bing Kang, Baining Guo

Related Works: Texture Synthesis basic element placement distribution … Similar basic element Similar placement distribution

Related Works: Texture Transfer [Efros and Freeman 2001], [Hertzmann et al. 2001]…

Related Works: Texture Design [Matusik et al. 2005] and other works…

Related Works: Texture Element Extraction Near-Regular Texture Analysis – [Liu et al. 2004], [Hays et al. 06]; – Limited to near-regular textures.

Texture Splicing = = + + new texture basic element placement distribution

Texture Analysis (1) self-similarity search

Self-Similarity Search Texture ImageNormalized Cross Correlation Value Sliding Window Template Patch Normalized Cross Correlation

Placement Distribution Extraction Texture ImageNormalized Cross Correlation Value Placement Distribution

Texture Analysis (2) Graph Cut

Graph Cut based Segmentation F B Minimize:

Different Types of Textures Foreground: Rigid Connected Foreground: Rigid Disjoint Background: Rigid Connected

New Texture Generation Texture A Texture B Distribution A Distribution BTexton Mask Deformation Field New Texture

Mapping The Points in Source and Target Distribution Get a mapping function f AB C AB measures the spatial distance between two points. Solved with minimum-cost bipartite graph matching.

Getting Deformation Field W Find a deformation field W AB which: – Map texture element p(x, y) in source distribution to its correspondent position in target distribution (f x (p), f y (p)); – Preserve the rigidity in the rigid area as much as possible. Rigid areaNon-rigid area

Getting Deformation Field W Solve ∆(p) = W AB (p) – p – Separate x and y: ∆(p) = (∆ x (p), ∆ y (p)); Energy Function:

Non-Rigid vs. Rigid (1) Texture Texton Mask Non-RigidRigid Deformation Field Result Deformation Field

Non-Rigid vs. Rigid (2) Texture Non-RigidRigid Deformation Field Result Deformation Field

Non-Rigid vs. Rigid (3) Texture Non-RigidRigid Deformation Field Result Deformation Field

Barycentric Interpolation sourceoutput W BA (q) q

Final Refinement Texture Synthesis [Lefebvre and Hoppe 2006] – Add fine details to the texture. – Fix the incorrectly deformed area in the texture. Before texture synthesisAfter texture synthesis

Splicing Result (1)

Splicing Result (2)

Splicing Result (3)

Self Splicing: Scaling

Self Splicing: Randomization

Self Splicing: Regularization

Self Splicing: Specific Rearrangement

Summary Texture Splicing: a novel method for texture editing. Simple idea: generate new textures with one texture’s element and another’s spatial placement distribution: – Self-similarity search; – Graph-cut based segmentation; – Image deformation with rigid constraint.

Summary (Cont’d) Simple but useful for users: – The user just need to provide two texture images. – The user can also directly editing the spatial placement. Require more interaction, but Provides more control on texture design.

Thank You! Any questions?