Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Example-Based Fractured Appearance L. Glondu, L. Muguercia, M. Marchal, C. Bosch, H. Rushmeier, G. Dumont and G. Drettakis.
1 Université de Montréal 2 INRIA Sophia Antipolis The Simulation of Paint Cracking and Peeling E. Paquette 1,2, P. Poulin 1, G. Drettakis 2.
1.  Texturing is a core process for modeling surface details in computer graphics applications › Texture mapping › Surface texture synthesis › Procedural.
Video Inpainting Under Constrained Camera Motion Kedar A. Patwardhan, Student Member, IEEE, Guillermo Sapiro, Senior Member, IEEE, and Marcelo Bertalm.
Surface Aging by Impacts E. Paquette 1,2, P. Poulin 1, G. Drettakis 2 1 Université de Montréal 2 iMAGIS/GRAVIR-REVES-INRIA.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
A new approach for modeling and rendering existing architectural scenes from a sparse set of still photographs Combines both geometry-based and image.
Texture Synthesis Tiantian Liu. Definition Texture – Texture refers to the properties held and sensations caused by the external surface of objects received.
Combining Human and Machine Capabilities for Improved Accuracy and Speed in Visual Recognition Tasks Research Experiment Design Sprint: IVS Flower Recognition.
Natural and Seamless Image Composition Wenxian Yang, Jianmin Zheng, Jianfei Cai, Senior Member, IEEE, Susanto Rahardja, Senior Member, IEEE, and Chang.
Fast Texture Synthesis using Tree-structured Vector Quantization Li-Yi Wei Marc Levoy Computer Graphics Group Stanford University.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Rodent Behavior Analysis Tom Henderson Vision Based Behavior Analysis Universitaet Karlsruhe (TH) 12 November /9.
Example-Based Color Transformation of Image and Video Using Basic Color Categories Youngha Chang Suguru Saito Masayuki Nakajima.
Detecting Image Region Duplication Using SIFT Features March 16, ICASSP 2010 Dallas, TX Xunyu Pan and Siwei Lyu Computer Science Department University.
Advanced lighting and rendering Multipass rendering.
Visual Querying By Color Perceptive Regions Alberto del Bimbo, M. Mugnaini, P. Pala, and F. Turco University of Florence, Italy Pattern Recognition, 1998.
Chamfer Matching & Hausdorff Distance Presented by Ankur Datta Slides Courtesy Mark Bouts Arasanathan Thayananthan.
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Tracking Video Objects in Cluttered Background
Automatic Photo Pop-up Derek Hoiem Alexei A. Efros Martial Hebert.
Background Estimation Mehdi Ghayoumi, MD Iftakharul Islam, Muslem Al-Saidi Department of Computer Science Kent State University, Kent, OH
Model Of Software Development Process For Virtual Environment –A Case Study - Shraddha Pathak.
Sana Naghipour, Saba Naghipour Mentor: Phani Chavali Advisers: Ed Richter, Prof. Arye Nehorai.
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.
SIGGRAPH 2003 Jingdan Zhang, Kun Zhou, Luiz Velho, Baining Guo, Heung-Yeung Shum.
Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller Center for Visual Computing Stony Brook University.
Abstract Some Examples The Eye tracker project is a research initiative to enable people, who are suffering from Amyotrophic Lateral Sclerosis (ALS), to.
UNDERSTANDING DYNAMIC BEHAVIOR OF EMBRYONIC STEM CELL MITOSIS Shubham Debnath 1, Bir Bhanu 2 Embryonic stem cells are derived from the inner cell mass.
Multimedia Databases (MMDB)
EE 492 ENGINEERING PROJECT LIP TRACKING Yusuf Ziya Işık & Ashat Turlibayev Yusuf Ziya Işık & Ashat Turlibayev Advisor: Prof. Dr. Bülent Sankur Advisor:
Reconstructing 3D mesh from video image sequences supervisor : Mgr. Martin Samuelčik by Martin Bujňák specifications Master thesis
Terrain Synthesis by Digital Elevation Models Howard Zhou, Jie Sun, Greg Turk, and James M. Rehg
Image recoloring induced by palette color associations Gary R. Greenfield, Donald H. House University of Richmond, Texas A&M University WSCG ' 2003.
Plug-in and tutorial development for GIMP- Cathy Irwin, 2004 The Development of Image Completion and Tutorial Plug-ins for the GIMP By: Cathy Irwin Supervisors:
Continuous Model Synthesis Paul Merrell and Dinesh Manocha In SIGGRAPH Asia 2008 발표 : 이성호.
Stylization and Abstraction of Photographs Doug Decarlo and Anthony Santella.
1 Perception and VR MONT 104S, Fall 2008 Lecture 21 More Graphics for VR.
Synthesis of Compact Textures for real-time Terrain Rendering Nader Salman 22 juin 2007 Encadrant : Sylvain Lefebvre.
Scene Completion Using Millions of Photographs James Hays, Alexei A. Efros Carnegie Mellon University ACM SIGGRAPH 2007.
TextureAmendment Reducing Texture Distortion in Constrained Parameterizations Yu-Wing TaiNational University of Singapore Michael S. BrownNational University.
2005/12/021 Content-Based Image Retrieval Using Grey Relational Analysis Dept. of Computer Engineering Tatung University Presenter: Tienwei Tsai ( 蔡殿偉.
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
Towards Real-Time Texture Synthesis With the Jump Map Steve Zelinka Michael Garland University of Illinois at Urbana-Champaign Thirteenth Eurographics.
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
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
Palette-based Photo Recoloring
Digital Video Library Network Supervisor: Prof. Michael Lyu Student: Ma Chak Kei, Jacky.
Photo VR Editor: A Panoramic and Spherical Environment Map Authoring Tool for Image-Based VR Browsers Jyh-Kuen Horng, Ming Ouhyoung Communications and.
Geometry Synthesis Ares Lagae Olivier Dumont Philip Dutré Department of Computer Science Katholieke Universiteit Leuven 10 August, 2004.
Enhancing Image-Based Aging Approaches Olivier Clément Eric Paquette.
Texture Synthesis by Image Quilting CS766 Class Project Fall 2004 Eric Robinson.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
Advisor : Ku-Yaw Chang Speaker : Ren-Li Shen /6/12.
Constrained Synthesis of Textural Motion for Animation Shmuel Moradoff Dani Lischinski The Hebrew University of Jerusalem.
SIGGRAPH 2007 Hui Fang and John C. Hart.  We propose an image editing system ◦ Preserve its detail and orientation by resynthesizing texture from the.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
CIRP Annals - Manufacturing Technology 60 (2011) 1–4 Augmented assembly technologies based on 3D bare-hand interaction S.K. Ong (2)*, Z.B. Wang Mechanical.
Acquiring, Stitching and Blending Diffuse Appearance Attributes on 3D Models C. Rocchini, P. Cignoni, C. Montani, R. Scopigno Istituto Scienza e Tecnologia.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching Link: singhashwini.mesinghashwini.me.
OCR Reading.
Introduction Multimedia initial focus
Detail Preserving Shape Deformation in Image Editing
You can check broken videos in this slide here :
Coding Approaches for End-to-End 3D TV Systems
Announcements Guest lecture next Tuesday
EE 492 ENGINEERING PROJECT
Gradient Domain Salience-preserving Color-to-gray Conversion
Presentation transcript:

Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab

2 Introduction Realistic image synthesis  Virtual reality, video games, special effects, etc. Aging (or weathering)  Many effects  Many objects  Time consuming

Multimedia Lab 3 Introduction Redesign iterations

Multimedia Lab 4 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 5 Objectives To build a system  To edit aging effects on textures  To increase realism  To reduce the amount of work  Adapted for artists adequate control interactive no complex parameters

Multimedia Lab 6 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 7 Previous Work Physically based methods [Dorsey and Hanharan 2000; Merillou et al. 2001; O’Brien et al. 2002; etc.]  Highly realistic results but lengthy calculations  Non-intuitive physical parameters Empirical methods [Chain et al. 2005; Gobron and Chiba 2001; Paquette et al. 2002; etc.]  More intuitive parameters Both approaches  Do not provide the control required by artists  Target a single aging effect Aging methods

Multimedia Lab 8 Previous Work Image based [Gu et al. 2006; Wang et al. 2006; etc.]  Capture the time-varying aspects of the material  Similar to our approach Focus of our approach  Simple capture process  Adequate control Aging methods

Multimedia Lab 9 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 10 Aging Editing Process Source image  Image, photograph  Containing aging effects Target aging mask  Binary image  Desired pattern Reproduction image  New aging effects Process overview

Multimedia Lab 11 Aging Editing Process Segmentation phase  Semi-automatic  Aged regions Elimination phase  Automatic  Aging removed Reproduction phase  Automatic  New aging effects Phase description R e d e s i g n i t e r a t i o n s

Multimedia Lab 12 Aging Editing Process Images summary

Multimedia Lab 13 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion 14

Multimedia Lab 14 Segmentation Phase Identifies aged regions Could be done with  Segmentation tools  Image editing software Stroke-based technique Lischinski et al. [2006]  Worked efficiently for semi-automatic identification

Multimedia Lab 15 Segmentation Phase Stroke-base technique - Video

Multimedia Lab 16 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion 17

Multimedia Lab 17 Elimination Phase Constrained texture synthesis Match the non-aged neighbourhood Search using ANN library Arya et al. [1998] The algorithm best match … new best match Elimination imageSource image copy the pixel color

Multimedia Lab 18 Elimination Phase The boundary pixels  Non-aged pixels in their neighbourhood  Must be filled first The aged region is filled iteratively Hole-filling

Multimedia Lab 19 Outline 20 Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 20 Reproduction Phase Extension of the elimination algorithm Consider the aged / non-aged context The new term

Multimedia Lab 21 Reproduction Phase Does not synthesize the entire image Only specified regions Iterative construction from multiple source images Aging effects transfer and combination

Multimedia Lab 22 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 23 Results Source imageElimination imageReproduction imageSource aging maskTarget aging mask

Multimedia Lab 24 Results Source imageElimination imageReproduction image

Multimedia Lab 25 Results Source imageElimination imageReproduction image

Multimedia Lab 26 Results Source imageAging masksReproduction image More results in the paper and the video…

Multimedia Lab 27 Results User interaction is minimal Interactive computation time Efficient for redesign iterations Efficiency 2.5 minutes - once 25 seconds - once 2 minutes every iteration 3 seconds every iteration Obtained on a PC with 3.2 GHz CPU and 3GB of RAM

Multimedia Lab 28 Limitations Apply only on surfaces  No fractures or deformations Camera-based texture acquisition  Specular lighting  Surface distortion Current implementation  Interactive on textures up to 512 x 512

Multimedia Lab 29 Outline Objectives Previous Work Aging Editing Process  Segmentation Phase  Elimination Phase  Reproduction Phase Results and Limitations Conclusion

Multimedia Lab 30 Conclusion A framework  To edit aging effects on textures  To reduce the amount of work needed during the redesign iterations Benefits  Appropriate for artists adequate control and interactivity no complex parameters  Works well for several types of aging effects

Multimedia Lab 31 Conclusion Synthesize the target aging mask  For numerous regions  Ex: scratches Handle layers in effects combination  Multiple effects over the same regions  Ex: dirt on top of rust Faster synthesis  To handle higher resolution textures Future work

Multimedia Lab 32 ? We would like to thank : And all our reviewers… Questions

Multimedia Lab 33 Previous Work Texture synthesis [Efros 1999; Hertzmann 2001; Kwatra 2003; Lefebvre 2006; Liang 2001; etc.]  Synthesis based on neighbourhood matching Our system  Extends from these algorithms  Specializes for the aging context Texture synthesis

Multimedia Lab 34 Previous Work Image analogies, Hertzmaan et al. [2001]  The output image is completely synthesized  Our approach uses a similar algorithm that synthesize only regions of the output  Our approach should be considered as an extension Texture synthesis

Multimedia Lab 35 Elimination Phase The replacement pixel is :  Selected from the non-aged pixels of the source image  One of the best neighbourhood matches The system seeks a replacement pixel that minimizes the following L 2 norm : The replacement pixel

Multimedia Lab 36 Elimination Phase An exhaustive search would require processing time far from interactive Thus, an approximation of the best match is found with the ANN library (Arya et al. [1998])  Approximate nearest neighbour searching algorithm based on a kd-tree structure  Our feature vector is composed of the RGB components of the non-aged pixels around the pixel to replace Interactivity