Inverse Texture Synthesis

Slides:



Advertisements
Similar presentations
Inverse Texture Synthesis Li-Yi Wei 1 Jianwei Han 2 Kun Zhou 1,2 Hujun Bao 2 Baining Guo 1 Harry Shum 1 1 Microsoft 2 Zhejiang University.
Advertisements

Lapped textures Emil Praun Adam Finkelstein Hugues Hoppe
Parallel Poisson Disk Sampling
Jiaping Wang1, Shuang Zhao2, Xin Tong1 John Snyder3, Baining Guo1
Interactive Deformation of Light Fields Billy Chen Eyal Ofek Heung-Yeung Shum Marc Levoy.
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model Ce Liu Heung-Yeung Shum Chang Shui Zhang CVPR 2001.
Large Mesh Deformation Using the Volumetric Graph Laplacian
Primal-dual Algorithm for Convex Markov Random Fields Vladimir Kolmogorov University College London GDR (Optimisation Discrète, Graph Cuts et Analyse d'Images)
Hongzhi Wu 1,2, Li-Yi Wei 1, Xi Wang 1, and Baining Guo 1 Microsoft Research Asia 1 Fudan University 2 Silhouette Texture.
HOPS: Efficient Region Labeling using Higher Order Proxy Neighborhoods Albert Y. C. Chen 1, Jason J. Corso 1, and Le Wang 2 1 Dept. of Computer Science.
Generating Classic Mosaics with Graph Cuts Y. Liu, O. Veksler and O. Juan University of Western Ontario, Canada Ecole Centrale de Paris, France.
Andrew Nealen and Marc Alexa, Discrete Geometric Modeling Group, TU Darmstadt, 2004 Fast and High Quality Overlap Repair for Patch-Based Texture Synthesis.
Line Segment Sampling with Blue-Noise Properties Xin Sun 1 Kun Zhou 2 Jie Guo 3 Guofu Xie 4,5 Jingui Pan 3 Wencheng Wang 4 Baining Guo 1 1 Microsoft Research.
Super-Resolution Texturing for Online Virtual Globes
Weakly supervised learning of MRF models for image region labeling Jakob Verbeek LEAR team, INRIA Rhône-Alpes.
L1 sparse reconstruction of sharp point set surfaces
Texture Synthesis on [Arbitrary Manifold] Surfaces Presented by: Sam Z. Glassenberg* * Several slides borrowed from Wei/Levoy presentation.
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
1.  Texturing is a core process for modeling surface details in computer graphics applications › Texture mapping › Surface texture synthesis › Procedural.
Lvdi Wang Tsinghua University Microsoft Research Asia Lvdi Wang Tsinghua University Microsoft Research Asia Kun Zhou Zhejiang University Kun Zhou Zhejiang.
Face Alignment at 3000 FPS via Regressing Local Binary Features
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
1 Image Completion using Global Optimization Presented by Tingfan Wu.
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) +=
Fast Texture Synthesis using Tree-structured Vector Quantization Li-Yi Wei Marc Levoy Computer Graphics Group Stanford University.
Texture Splicing Yiming Liu, Jiaping Wang, Su Xue, Xin Tong, Sing Bing Kang, Baining Guo.
High-Quality Video View Interpolation
TEXTURE SYNTHESIS PEI YEAN LEE. What is texture? Images containing repeating patterns Local & stationary.
Andrew Nealen and Marc Alexa, Discrete Geometric Modeling Group, TU Darmstadt, 2003 Hybrid Texture Synthesis Andrew Nealen Marc Alexa Discrete Geometric.
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.
Texture Optimization for Example-based Synthesis
SIGGRAPH 2003 Jingdan Zhang, Kun Zhou, Luiz Velho, Baining Guo, Heung-Yeung Shum.
Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.
Adaptive Real-Time Rendering of Planetary Terrains WSCG 2010 Raphaël Lerbour Jean-Eudes Marvie Pascal Gautron THOMSON R&D, Rennes, France.
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.
1 Reconstructing head models from photograph for individualized 3D-audio processing Matteo Dellepiane, Nico Pietroni, Nicolas Tsingos, Manuel Asselot,
Non-Photorealistic Rendering and Content- Based Image Retrieval Yuan-Hao Lai Pacific Graphics (2003)
Synthesis of Compact Textures for real-time Terrain Rendering Nader Salman 22 juin 2007 Encadrant : Sylvain Lefebvre.
Geodesic Saliency Using Background Priors
TextureAmendment Reducing Texture Distortion in Constrained Parameterizations Yu-Wing TaiNational University of Singapore Michael S. BrownNational University.
Epitomic Location Recognition A generative approach for location recognition K. Ni, A. Kannan, A. Criminisi and J. Winn In proc. CVPR Anchorage,
2D Texture Synthesis Instructor: Yizhou Yu. Texture synthesis Goal: increase texture resolution yet keep local texture variation.
Jigsaws: joint appearance and shape clustering John Winn with Anitha Kannan and Carsten Rother Microsoft Research, Cambridge.
using Radial Basis Function Interpolation
Geometry Synthesis Ares Lagae Olivier Dumont Philip Dutré Department of Computer Science Katholieke Universiteit Leuven 10 August, 2004.
Thank you for the introduction
Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong.
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 hole-filling. Agenda Project 2: Will be up tomorrow Due in 2 weeks Fourier – finish up Hole-filling (texture synthesis) Image blending.
SIGGRAPH 2007 Hui Fang and John C. Hart.  We propose an image editing system ◦ Preserve its detail and orientation by resynthesizing texture from the.
Texture Analysis and Synthesis. Texture Texture: pattern that “looks the same” at all locationsTexture: pattern that “looks the same” at all locations.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Image-Guided Weathering: A New Approach Applied to Flow Phenomena C. Bosch 1, P. Y. Laffont, H. Rushmeier, J. Dorsey, G. Drettakis Yale University – REVES/INRIA.
Two Patch-based Algorithms for By-example Texture Synthesis
Announcements Project 4 out today help session at the end of class.
Detail Preserving Shape Deformation in Image Editing
Real-Time Image Mosaicing
By: Kevin Yu Ph.D. in Computer Engineering
A Computational Darkroom for BW Photography
Perfect Spatial Hashing
Interactive photo-realistic 3D digital prototyping
Image Quilting for Texture Synthesis & Transfer
A Computational Darkroom for BW Photography
Analysis of Contour Motions
Random Neural Network Texture Model
Presentation transcript:

Inverse Texture Synthesis Li-Yi Wei1 Jianwei Han2 Kun Zhou1,2 Hujun Bao2 Baining Guo1 Harry Shum1 1Microsoft 2Zhejiang University

Example-based texture synthesis For a small input texture produce an arbitrarily large output with similar look Why? may not possible to obtain large input texture synthesis input output

Inverse texture synthesis From a large input texture produce a small output that best summarizes input inverse texture synthesis output input

Why? Textures are getting large Advances in scanning technology High dimensionality: time-varying, BRDF Expensive to store, transmit, compute So why we need this? Textures are getting larger, making them more expensive to store, transmit, and compute. Yale University MSR Asia Columbia University

Overview inverse texture synthesis input output (large) (small) texturing (slow) (fast) Inverse texture synthesis can solve these problems. Given a large input, the algorithm will produce a small compaction that retains vital information of the input. The compaction can be used for texturing with similar visual results from the original input, with faster computation and smaller memory consumption. similar quality

Related work: image compression pixel-wise identical compress decompress inverse synth texture synth input perceptual similar

Related work: epitome Epitome [Jojic et al. 2003] Jigsaw [Kannan et al. 2007] Major source of inspiration for us For general images, not just textures We provide better quality Bidirectional similarity [Simakov et al. 2008] Factoring repeated content [Wang et al. 2008]

Related work: manual crop stationary globally varying original manual crop our result

Globally-varying textures Markov Random Field (MRF) textures local & stationary Globally-varying textures local, but not necessarily stationary MRF globally varying

Globally varying textures Previous work MRF input → globally varying output texture-by-numbers in Image analogies [Hertzmann et al. 2001] progressively variant textures [Zhang et al. 2003] texture design and morphing [Matusik et al. 2005] Globally varying input appearance manifold [Wang et al. 2006] spatially & time varying BRDF [Gu et al. 2006] context-aware texture [Lu et al. 2007]

Globally varying textures Definition texture + control maps Examples of control maps user-specified colors [Hertzmann et al. 2001] spatially-varying parameters [Gu et al. 2006] weathering degree-map [Wang et al. 2006] context information [Lu et al. 2007] texture (paint crack) control map (paint thickness)

Globally varying textures Including time-varying textures as well Large data size! time-varying BRDF [Gu et al. 2006] 512 x 512 x 33, 288 MB context-aware texture [Lu et al. 2007] 1226 x 978 x 50, 35 MB

Inverse texture synthesis Compacting globally varying textures including both texture + control map output compaction inverse synthesis texture control texture control map input

Compaction as summary of original Re-synthesis with user control map faster slower forward synthesis user control + compaction re-synthesis from compaction re-synthesis from original

Inverse Texture Synthesis Applicable to MRF textures no control map homogenized result manual cropping ? original re-synthesis

Inverse Texture Synthesis Manual cropping unsuitable for globally variant texture no matter where you put the window our compaction manual crop black purple orange original from compaction from manual crop

forward term [Kwatra et al. 2005] Basic formulation Inspired by texture optimization [Kwatra et al. 2005] inverse term (New!) forward term [Kwatra et al. 2005] xp Zp best match zq xq best match Z (output) X (input)

Energy plot energy original compaction size

Why both terms? inverse term preserves all input features forward inverse term preserves all input features forward term avoids artifacts in compaction f-only missing feature both i-only garbage both i-only discontinuity both

Comparing with epitome [Jojic et al. 2003] Similar to our method but only inverse term blur, discontinuity epitome epitome our our original original

Comparing with epitome [Jojic et al. 2003] Re-synthesis our epitome our original original

Solver How to solve this? Texture optimization [Kwatra et al. 2005] Discrete solver [Han et al. 2006]

Optimization [Kwatra et al. 2005] NO inverse term forward term [Kwatra et al. 2005] E-step fix xq argminz E(x,z) least square M-step fix Z argminxq |xq-zq|2 search fix xq xq Zq zq xq Z argminxq |xq-zq|2 X

forward term [Kwatra et al. 2005] Our solver inverse term forward term [Kwatra et al. 2005] E-step fix xq argminz E(x,z) least square M-step (forward) fix Z argminxq |xq-zq|2 search xp xp zp xq Zq discrete solver [Han et al. 2006] M-step (inverse) fix xp argminzp |xp-zp|2 discrete solver zq xq Z argminxq |xq-zq|2 discrete solver X

Results

Results output control compaction 1282 original (paint crack) 799 x 546 from orig. 84555 sec from comp. 1131 sec

Compaction size on quality 799 x 546 5122 2562 1282

Compaction size on quality 799 x 546 (original) 5122 2562 1282

Re-synthesis without control map stationary only comp. original re-synthesis

GPU synthesis – small texture better Extension from [Lefebvre & Hoppe 2005] 3 fps, original 6 fps, compact cheese mold 1214 x 1212 compaction 1282 3.5 fps, original 7.0 fps, compact dirt 271x481 original

Limitation: Correlation between texture & control original reconstruction compaction

Why little squares. Instead of, e. g Why little squares? Instead of, e.g. a set of texton [Leung & Malik 2001] Most general compaction utilizable for any synthesis algorithm GPU synthesis Looks nice I like little squares visual summary & visualization

Orientation field for anisotropic textures Orientation field w as part of energy function E(x, z) → E(x, z; w) Good orientation field yields better solution comp. no w comp. with w original orientation field

Results: orientation field just mention this in a quick pass Paris et al. 04 original manual + interp ours

Results: orientation field Paris et al. 04 original manual + interp ours

Results: orientation field Paris et al. 04 original manual + interp ours

Results: orientation field Paris et al. 04 original manual + interp ours

Future work Higher dimensional textures e.g. video General images, not just textures Bidirectional similarity [Simakov et al. CVPR 2008] Image compression

Acknowledgements Yale graphics group Columbia graphics group Sylvain Lefebvre Hughes Hoppe Matusik et al. 2005 Mayang.com Jiaping Wang Xin Tong Jian Sun Frank Yu Bennett Wilburn Eric Stollnitz Dwight Daniels Reviewers Dinesh Manocha Ming Lin Chas Boyd Brandon Lloyd Avneesh Sud Billy Chen

Thank You!