Course: Structure-Aware Shape Processing Introduction to Geometric ‘Structure’ Extracting Structures –analysis of Individual Models –analysis of Shape.

Slides:



Advertisements
Similar presentations
1/50 Photo-Inspired Model-Driven 3D Object Modeling Kai Xu 1,2 Hanlin Zheng 3 Hao (Richard) Zhang 2 Daniel Cohen-Or 4 Ligang Liu 3 Yueshan Xiong 1 1 National.
Advertisements

Animosaics Kaleigh Smith, Yunjun Liu, and Allison Klein McGill University Eurographics Symposium on Computer Animation 2005.
RGB-D object recognition and localization with clutter and occlusions Federico Tombari, Samuele Salti, Luigi Di Stefano Computer Vision Lab – University.
Yunhai Wang 1 Minglun Gong 1,2 Tianhua Wang 1,3 Hao (Richard) Zhang 4 Daniel Cohen-Or 5 Baoquan Chen 1,6 5 Tel-Aviv University 4 Simon Fraser University.
Toward Automatic Music Audio Summary Generation from Signal Analysis Seminar „Communications Engineering“ 11. December 2007 Patricia Signé.
Interactive Inverse 3D Modeling James Andrews Hailin Jin Carlo Séquin.
Fast and Extensible Building Modeling from Airborne LiDAR Data Qian-Yi Zhou Ulrich Neumann University of Southern California.
Structure Recovery by Part Assembly Chao-Hui Shen 1 Hongbo Fu 2 Kang Chen 1 Shi-Min Hu 1 1 Tsinghua University 2 City University of Hong Kong.
Biologically Inspired AI (mostly GAs). Some Examples of Biologically Inspired Computation Neural networks Evolutionary computation (e.g., genetic algorithms)
Model-Driven 3D Content Creation as Variation Hao (Richard) Zhang – 张皓 GrUVi Lab, Simon Fraser University (SFU) HKUST, 04/21/11 TAUZJUNUDT SFU.
PARAMETRIC RESHAPING OF HUMAN BODIES IN IMAGES SIGGRAPH 2010 Shizhe Zhou Hongbo Fu Ligang Liu Daniel Cohen-Or Xiaoguang Han.
Example Based 3D Shape Completion Mark Pauly 1,2, Niloy J. Mitra 1, Joachim Giesen 2, Markus Gross 2, Leonidas J. Guibas 1 1 Stanford University 2 ETH,
Learning to Advertise. Introduction Advertising on the Internet = $$$ –Especially search advertising and web page advertising Problem: –Selecting ads.
Interactive Hairstyle Modeling Using a Sketching Interface Xiaoyang Mao Kouichi Kashio Hiroyuki Kato Atsumi Imamiya CGGM 2002.
Prior Knowledge for Part Correspondence Oliver van Kaick 1, Andrea Tagliasacchi 1, Oana Sidi 2, Hao Zhang 1, Daniel Cohen-Or 2, Lior Wolf 2, Ghassan Hamarneh.
Guilford County Sci Vis V204.01
Jon Chippindall Class Teacher and Computing Leader Crumpsall Lane Primary CAS Master Teacher
A Practical System for Modelling Body Shapes from Single View Measurements Yu Chen 1, Duncan Robertson 2, Roberto Cipolla 1 Department of Engineering,
Abstraction of Man-Made Shapes Ravish Mehra 1,2, Qingnan Zhou 1, Jeremy Long 4, Alla Sheffer 1, Amy Gooch 4, Niloy J. Mitra 2,3 1 Univ. of British Columbia.
The Three R’s of Vision Jitendra Malik.
Symmetry Hierarchy of Man-Made Objects Yanzhen Wang 1,2, Kai Xu 1,2, Jun Li 2, Hao Zhang 1, Ariel Shamir 3, Ligang Liu 4, Zhiquan Cheng 2, Yueshan Xiong.
Integrating museum systems: Accessing collections information at the Victoria and Albert Museum Christopher Marsden Sarah Winmill, Frances Lloyd-Baynes.
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.
An Algebraic Model for Parameterized Shape Editing Martin Bokeloh, Stanford Univ. Michael Wand, Saarland Univ. & MPI Hans-Peter Seidel, MPI Vladlen Koltun,
Architecture styles Pipes and filters Object-oriented design Implicit invocation Layering Repositories.
Terrain Synthesis by Digital Elevation Models Howard Zhou, Jie Sun, Greg Turk, and James M. Rehg
SPONSORED BY Data-driven Segmentation and Labeling of Freehand Sketches Zhe Huang, Hongbo Fu, Rynson W.H. Lau City University of Hong Kong.
Organizing Heterogeneous Scene Collections through Contextual Focal Points Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or, Hui.
Computer Vision Why study Computer Vision? Images and movies are everywhere Fast-growing collection of useful applications –building representations.
Midterm Stats Min: 16/38 (42%) Max: 36.5/38 (96%) Average: 29.5/36 (78%)
Fuzzy Genetic Algorithm
Evolving Virtual Creatures & Evolving 3D Morphology and Behavior by Competition Papers by Karl Sims Presented by Sarah Waziruddin.
1 Reconstructing head models from photograph for individualized 3D-audio processing Matteo Dellepiane, Nico Pietroni, Nicolas Tsingos, Manuel Asselot,
12/7/10 Looking Back, Moving Forward Computational Photography Derek Hoiem, University of Illinois Photo Credit Lee Cullivan.
Alternative Architecture for Information in Digital Libraries Onno W. Purbo
June 26, 2003 Dept. of Computer Science Memorial University of Newfoundland Structuring Interactive Cluster Analysis Wayne Oldford University of Waterloo.
A Practical Framework for Constructing Structured Drawings Salman Cheema Sarah BuchananSumit Gulwani Joseph J. LaViola Jr. References [ 1] Cheema, S.,
Temporally Coherent Completion of Dynamic Shapes AUTHORS:HAO LI,LINJIE LUO,DANIEL VLASIC PIETER PEERS,JOVAN POPOVIC,MARK PAULY,SZYMON RUSINKIEWICZ Presenter:Zoomin(Zhuming)
3D Object Morphing CS5245 Vision and Graphics for Special Effects.
2/29/20121 Optimizing LCLS2 taper profile with genetic algorithms: preliminary results X. Huang, J. Wu, T. Raubenhaimer, Y. Jiao, S. Spampinati, A. Mandlekar,
Sponsored by Deformation-Driven Topology-Varying 3D Shape Correspondence Ibraheem Alhashim Kai Xu Yixin Zhuang Junjie Cao Patricio Simari Hao Zhang Presenter:
Course: Structure-Aware Shape Processing Hao (Richard) Zhang Simon Fraser University (SFU), Canada Structural Hierarchies Course: Structure-Aware Shape.
Computer Vision, CS766 Staff Instructor: Li Zhang TA: Yu-Chi Lai
Enhancing Image-Based Aging Approaches Olivier Clément Eric Paquette.
Online Learning and Evaluation A Review. High Impact Learning Solutions Instructor-led Training Structured Meetings On-the-Job Coaching/Mentoring Virtual.
Lights,Camera, Action &… Reaction, scrapbook, illustrative photos Summer 2005 Presented by Your Name.
CENG 789 – Digital Geometry Processing 10- Data-Driven Shape Analysis
Pen Based User Interface II CSE 481b January 25, 2005.
Stackabilization Honghua Li, Ibraheem Alhashim, Hao Zhang, Ariel Shamir, Daniel Cohen-Or.
Course: Structure-Aware Shape Processing Introduction to Geometric ‘Structure’ Extracting Structures –analysis of Individual Models –analysis of Shape.
Automated Geo-referencing of Images Dr. Ronald Briggs Yan Li GeoSpatial Information Sciences The University.
Shape2Pose: Human Centric Shape Analysis CMPT888 Vladimir G. Kim Siddhartha Chaudhuri Leonidas Guibas Thomas Funkhouser Stanford University Princeton University.
Structure Recovery by Part Assembly Chao-Hui Shen, Hongbo Fu, Kang Chen and Shi-Min Hu Tsinghua University City University of Hong Kong Presented by: Chenyang.
Student: Shunan Shi Professor: Hao Zhang CMPT888.
Co-Hierarchical Analysis of Shape Structures Oliver van Kaick 1,4 Kai Xu 2 Hao Zhang 1 Yanzhen Wang 2 Shuyang Sun 1 Ariel Shamir 3 Daniel Cohen-Or 4 4.
Structure-Aware Shape Processing Part III Example Applications Martin Bokeloh Niloy Mitra Michael Wand Hao Zhang Daniel Cohen-Or Martin Bokeloh.
Prior Knowledge for Part Correspondence
New computer-aided design tools applied on engineering design education A. Martin-Erro (1), M. Dominguez (1), M.M. Espinosa(1)   (1) UNED-ETSII (Ingeniería.
INTRODUCTION TO GEOGRAPHICAL INFORMATION SYSTEM
Layered Analysis of Irregular Facades via Symmetry Maximization
Lecture Week 4 Images.
Fast Preprocessing for Robust Face Sketch Synthesis
Computing Curriculum Plans
Local Feature Extraction Using Scale-Space Decomposition
Image Based Modeling and Rendering (PI: Malik)
CSc4730/6730 Scientific Visualization
Topology-Varying 3D Shape Creation via Structural Blending
Authors: Barry Smyth, Mark T. Keane, Padraig Cunningham
Computing Curriculum Plans
Presentation transcript:

Course: Structure-Aware Shape Processing Introduction to Geometric ‘Structure’ Extracting Structures –analysis of Individual Models –analysis of Shape Collections (co-analysis) –Structural Hierarchies Manipulating Structures –Modeling as Structural Variations –Structure-guided Design –Organization + Exploration of Shape Collections Future Directions Course structure

Course: Structure-Aware Shape Processing Modeling as Structural Variation Niloy J. MitraMichael Wand Hao Zhang Daniel Cohen-Or Vladimir KimQi-Xing Huang

Course: Structure-Aware Shape Processing Inspiration  a readily usable digital 3D model Inspiration? Modeling: 3D content creation

Course: Structure-Aware Shape Processing Inspiration = real-world data Realistic reconstruction

Course: Structure-Aware Shape Processing Creation of novel 3D shapes Inspiration = design, sketch, photo, other examples sketch High demand in VFX, games, simulation, VR, … Focus on creative modeling

Course: Structure-Aware Shape Processing 2D-to-3D: an ill-posed problem –Shape from shading, sketch-based modeling, … Creation from scratch is hard: job for skilled artists Main reason why graphics is not as ubiquitous as we wanted it to be  Jim Kajia’s SIG’11 Award Talk 3D content creation is hard

Course: Structure-Aware Shape Processing Models created are meant for subsequent use Desire to create readily usable 3D models Usable 3D content even harder

Course: Structure-Aware Shape Processing Models created are meant for subsequent use Desire to create readily usable 3D models Usability: higher-level information beyond low-level mesh –Part or segmentation information –Structural relations between parts –Correspondence to relevant models, etc. Hard shape analysis problems! Usable 3D content even harder

Course: Structure-Aware Shape Processing Reuse existing 3D models and associated information Data- or model-driven approach: creation is driven by or based on existing (pre-analyzed) models Key: model reuse

Course: Structure-Aware Shape Processing Reuse existing 3D models and associated info Data- or model-driven approach: creation is driven by or based on existing (pre-analyzed) models Key: model reuse

Course: Structure-Aware Shape Processing New model created by varying existing models Paradigm I: much like shape editing Modeling as variation Variation as modification of an existing model, e.g., a warp or a deformation

Course: Structure-Aware Shape Processing New model created by varying existing models Paradigm I: much like shape editing Paradigm II: shape synthesis Modeling as variation Variation as modification of an existing model, e.g., a warp or a deformation Variation by part composition, from multiple models

Course: Structure-Aware Shape Processing Available models are assumed to be structurally valid or proper New model should maintain that validity, but only preserve the “essential structures” Conflicting goals = challenge = “fit & diverse”: –Fit: structure preservation from existing models –Diverse: encourage significant deviation from examples = novelty or creativity Two conflicting goals

Course: Structure-Aware Shape Processing iWires: [Gal et al. 2009] Component-wise controllers: [Zheng et al. 2010] Photo-inspired modeling: [Xu et al. 2011] Structural retargeting: [Lin et al. 2011, Bokeloh et al. 2012, Bao et al. 2012, Yeh et al. 2013, Zhang et al. 2013] Topology-varying blending: [Alhashim et al. 2014] Modeling by deformation

Course: Structure-Aware Shape Processing Wires as control or deformation handles [Singh & Fiume 1999] Editing preserves structural relations, e.g., symmetry, co-planarity, etc. iWire: analyze-and-edit [Gal et al. 2009]

Course: Structure-Aware Shape Processing Cuboids and generalized cylinders as control handles Use the analyze-and-edit paradigm like iWires Preserve structural relations among controllers: symmetry and proximity Component-wise controllers [Zheng et al. 2010]

Course: Structure-Aware Shape Processing Not editing; modeling inspired by a single photograph Warp an existing 3D model to fit object silhouette in the photograph Structure preservation ensures a coherent 3D model Photo-inspired modeling [Xu et al. 2011]

Course: Structure-Aware Shape Processing photo Photo-inspired modeling Use the controllers from [Zheng et al. 2010] [Xu et al. 2011]

Course: Structure-Aware Shape Processing Use the controllers from [Zheng et al. 2010] photo Photo-inspired modeling Retrieved candidate 3D model [Xu et al. 2011]

Course: Structure-Aware Shape Processing Result of deformation to fit silhouette photo Use the controllers from [Zheng et al. 2010] Photo-inspired modeling [Xu et al. 2011] Retrieved candidate 3D model

Course: Structure-Aware Shape Processing Use the controllers from [Zheng et al. 2010] Structure preservation at work symmetry [Xu et al. 2011]

Course: Structure-Aware Shape Processing proximity Use the controllers from [Zheng et al. 2010] Structure preservation at work [Xu et al. 2011] symmetry

Course: Structure-Aware Shape Processing additional optimization Use the controllers from [Zheng et al. 2010] Structure preservation at work proximity symmetry [Xu et al. 2011]

Course: Structure-Aware Shape Processing output Use the controllers from [Zheng et al. 2010] Structure preservation at work [Xu et al. 2011] additional optimization proximity symmetry

Course: Structure-Aware Shape Processing Key analysis: regularity detection and organization Repetition of 1D or 2D regular patterns is relatively easy Retarget amid irregularity is hard Structural retargeting Key words: analyze-and-stretch; pattern repetition rather than geometric stretch!

Course: Structure-Aware Shape Processing [Lin et al. 2011]: –Hierarchical structural organization of façade elements obtained manually –Auto decompose facades into 1D sequences and retarget sequence by sequence Retarget with semi-auto analysis [Lin et al. 2011]

Course: Structure-Aware Shape Processing Automatic hierarchical decomposition of irregular 2D facades Optimal decomposition via SYMAX (next week’s talk by Wallace) Retarget facade by altering the generative hierarchical model Automatic analysis [Zhang et al. 2013]

Course: Structure-Aware Shape Processing Structure-aware blending between 3D shapes with different topologies Topology-varying blending or morphing [Alhashim et al. 2014]

Course: Structure-Aware Shape Processing Modeling by example [Funkhouser et al. 2004] Fit & diverse: [Xu et al. 2012] Structure recovery by part assembly: [Shen et al. 2012] Replacing functional sub-structures: [Zheng et al. 2013] Modeling by part composition

Course: Structure-Aware Shape Processing New models composed by parts retrieved from an existing data repository Key: retrieve relevant parts by geometric similarity of parts Many variants to date [Funkhouser et al. 2004] Modeling by example

Course: Structure-Aware Shape Processing Major difference: instead of generating one model at a time, evolve a set of shapes together Inspired by the biological process of evolution [Xu et al. 2012] Set evolution

Course: Structure-Aware Shape Processing Off-springs by part mutation (warp) and cross-over (reassembly of parts by fuzzy replaceability): leads to diversity Design gallery: user specifies “like” or “dislike” to define fitness function [Xu et al. 2012] Fit & diverse

Course: Structure-Aware Shape Processing Modeling from a single Kinect depth scan + RGB image Unlike [Xu et al. 2011], model is built by part assembly from multiple shapes, which is more versatile than just warping one candidate model [Shen et al. 2012] Structure recovery by assembly

Course: Structure-Aware Shape Processing Detect a specific type of common sub-structures in a set of shapes by sub-graph matching: a step towards functionality analysis Replacement can cross different object categories [Zheng et al. 2013] Replacing sub-structures

Course: Structure-Aware Shape Processing Deformation applied mainly for editing/morphing or to model by fitting to something, e.g., a photo, a sketch, or a Kinect scan Part combination mainly for creating novel shapes There are more structural changes with part combination Deform vs. part combination