Program
Date & Time
Technical Papers
Image & Video Applications
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 158
Automatic Generation of Destination Maps
A system for automatic generation of destination maps: navigational aids designed to show anyone within a region how to reach a small set of locations.
TOG Article: 161
Video Quality Assessment for Computer Graphics Applications
The proposed metric predicts the perceived quality of natural as well as rendered video sequences, even if the input videos have different dynamic ranges.
TOG Article: 159
Resizing by Symmetry-Summarization
Understanding the symmetry content inside an image allows image resizing via summarization. This provides extra space for effective image resizing.
TOG Article: 160
A Comparative Study of Image Retargeting
A comprehensive study and analysis of image-retargeting methods and human perception of resized images.
Friday
17 December
2:15 PM - 4:00 PM
Technical Papers
Computational Imagery
Room E1-E4

Presented in Korean / 한국어로 발표 됨

TOG Article: 172a
Computational Rephotography
A real-time estimation and visualization technique that helps users match the viewpoint of a reference photograph. Users can reach the desired viewpoint by following this visualization technique at capture time.
TOG Article: 171
Optimizing Continuity in Multiscale Imagery
A method for creation of visually smooth mipmap pyramids from imagery at several scales introduces techniques to reduce ghosting and blurring, and demonstrates continuous zooms from space to ground level.
TOG Article: 170
Computational Highlight Holography
Computational highlight holography converts 3D models into mechanical "holograms". Small grooves are milled into a surface, and each produces a reflected or refracted highlight that moves with correct binocular and motion parallax.
TOG Article: 172
Axial-Cones: Modeling Spherical Catadioptric Cameras for Wide-Angle Light Field Rendering
This novel geometric ray modeling for non-central spherical catadioptric cameras allows fast and exact wide-FOV lightfield rendering. The method enables perspective algorithms to be directly applied to catadioptric cameras.
Saturday
18 December
9:00 AM - 10:45 AM
Technical Papers
Reconstructing and Editing Geometry
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 152
Analysis, Reconstruction and Manipulation Using Arterial Snakes
Arterial snakes for analyzing and reconstructing the arterial surfaces and decomposing them into a set of semantically useful arterial components, which benefits the manipulation of such surfaces.
TOG Article: 150
Cone Carving for Surface Reconstruction
Visibility cones carve the ambient space of the shape from inside out to better approximate the signed distances to the shape near holes and infer correct surface topology for reconstruction.
TOG Article: 151
Automatic Reconstruction of Tree Skeletal Structures From Point Clouds
An automatic approach to reconstructing tree skeletal structures from point clouds that are often noisy, incomplete, and have trees with overlapping crowns.
TOG Article: 153
Editing Operations for Irregular Vertices in Triangle Meshes
An interactive editing framework that provides control over the type, location, and number of irregular vertices in the input mesh.
Friday
17 December
9:00 AM - 10:45 AM
Technical Papers
Rendering
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 144
A Progressive Error Estimation Framework for Photon Density Estimation
A first-error estimation framework for photon-density estimation methods that works under complex and general light transport configurations.
TOG Article: 142
Consistent Normal Interpolation
A simple modification of Phong normal interpolation that allows physically plausible reflections yet changes smoothly across the surface.
TOG Article: 143
Combining Global and Local Virtual Lights for Detailed Glossy Illumination
This global-illumination solution for glossy inter-reflections handles the low-rank (dense) and high-rank (sparse) lighting components separately, using visibility clustering and a novel local-lights technique.
TOG Article: 141
A Practical Appearance Model for Dynamic Facial Color
This animatable appearance model for skin-color animation, based on real measurements of melanin and hemoglobin, is efficiently coupled with a geometric facial-animation rig.
Thursday
16 December
2:15 PM - 4:00 PM
Technical Papers
Korean Technical Papers Session
Room E5

Presented in Korean / 한국어로 발표 됨

TOG Article: 172a
Computational Rephotography
A real-time estimation and visualization technique that helps users match the viewpoint of a reference photograph. Users can reach the desired viewpoint by following this visualization technique at capture time.
TOG Article: 140
Morphable Crowds
A novel method of blending crowd animations into a new crowd that exhibits the intervening formations and motion styles at an arbitrary scale.
TOG Article: 176
Detail-Preserving Fully-Eulerian Interface Tracking Framework
This paper presents a new fully Eulerian interface tracking framework that preserves fine details of liquid.
TOG Article: 154
Real-Time Collision Culling of a Million Bodies on Graphics Processing Units
A very fast, parallel, broad-phase collision-culling algorithm that can deal with a million objects. The algorithm is integrated with real-time simulation of particle dynamics and rigid-body dynamics.
Friday
17 December
2:15 PM - 4:00 PM
Technical Papers
Sampling & Filtering
Room E5

Presented in English / 영어로 발표 됨

TOG Article: 169
Accelerating Spatially Varying Gaussian Filters
An acceleration method for approximating spatially varying Gaussian filters. The method offers better filtering quality over the standard bilateral filter with a moderate increase in computational complexity.
TOG Article: 166
Parallel Poisson Disk Sampling With Spectrum Analysis on Surfaces
A fast, parallel Poisson disk-surface sampling algorithm suitable for dynamic meshes and introduction of a spectrum-analysis method for directly evaluating sample distribution on arbitrary manifold surfaces.
TOG Article: 168
Spectral Sampling of Manifolds
This sampling method based on spectral analysis of manifolds results in faithful reconstructions, and it is efficient, out-of-core, feature-sensitive, intuitive to control, and simple to implement.
TOG Article: 167
Anisotropic Blue Noise Sampling
Anisotropic blue noise sampling extends traditional isotropic dart throwing, relaxation, and Fourier-spectrum analysis techniques for anisotropic scenarios. Applications include stippling, re-meshing, rendering, and object placement.
Friday
17 December
4:15 PM - 6:30 PM
Technical Papers
Volumetric Modeling and Rendering
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 180
Volumetric Modeling With Diffusion Surfaces
This paper proposes Diffusion Surfaces (DSs), a new primitive for volumetric modeling, and a user interface tailored to modeling objects whose inner structure has rotational symmetries.
TOG Article: 179
Fast Parallel Surface and Solid Voxelization on GPUs
Data-parallel methods for conservative and 6-separating surface voxelization and for solid voxelization, including a novel octree-based sparse solid voxelization approach.
TOG Article: 177
Unbiased, Adaptive Stochastic Sampling for Rendering Inhomogeneous Participating Media
This unbiased and adaptive sampling technique for generating scattering events accelerates rendering of highly inhomogeneous participating media inbyone to two orders of magnitude.
TOG Article: 178
A Hierarchical Volumetric Shadow Algorithm for Single Scattering
An incremental, hierarchical algorithm for rendering volumetric shadows in single-scattering participating media.
Saturday
18 December
2:15 PM - 4:00 PM
Technical Papers Fast Forward
Technical Papers Fast Forward Session
Auditorium

Presented in English / 영어로 발표 됨

TOG Article: 183
Data-Driven Suggestions for Creativity Support in 3D Modeling
This paper introduces data-driven suggestions for 3D modeling. The approach computes and presents components that can augment the artist's current shape.
TOG Article: 180
Volumetric Modeling With Diffusion Surfaces
This paper proposes Diffusion Surfaces (DSs), a new primitive for volumetric modeling, and a user interface tailored to modeling objects whose inner structure has rotational symmetries.
TOG Article: 172a
Computational Rephotography
A real-time estimation and visualization technique that helps users match the viewpoint of a reference photograph. Users can reach the desired viewpoint by following this visualization technique at capture time.
TOG Article: 169
Accelerating Spatially Varying Gaussian Filters
An acceleration method for approximating spatially varying Gaussian filters. The method offers better filtering quality over the standard bilateral filter with a moderate increase in computational complexity.
TOG Article: 137
Stable Inverse Dynamic Curves
This technique automatically converts any 2D curve into the rest shape of a dynamic curve that can be subsequently animated.
TOG Article: 166
Parallel Poisson Disk Sampling With Spectrum Analysis on Surfaces
A fast, parallel Poisson disk-surface sampling algorithm suitable for dynamic meshes and introduction of a spectrum-analysis method for directly evaluating sample distribution on arbitrary manifold surfaces.
TOG Article: 140
Morphable Crowds
A novel method of blending crowd animations into a new crowd that exhibits the intervening formations and motion styles at an arbitrary scale.
TOG Article: 175
Multi-Phase Fluid Simulations Using Regional Level Sets
Simulation of multi-phase liquid interactions with each component registered to the regional level-set graph.
TOG Article: 179
Fast Parallel Surface and Solid Voxelization on GPUs
Data-parallel methods for conservative and 6-separating surface voxelization and for solid voxelization, including a novel octree-based sparse solid voxelization approach.
TOG Article: 152
Analysis, Reconstruction and Manipulation Using Arterial Snakes
Arterial snakes for analyzing and reconstructing the arterial surfaces and decomposing them into a set of semantically useful arterial components, which benefits the manipulation of such surfaces.
TOG Article: 171
Optimizing Continuity in Multiscale Imagery
A method for creation of visually smooth mipmap pyramids from imagery at several scales introduces techniques to reduce ghosting and blurring, and demonstrates continuous zooms from space to ground level.
TOG Article: 155
Piles of Objects
This method for directly modeling piles of objects in multibody simulations improves computation time and achieves accurate or desired piling effects.
TOG Article: 170
Computational Highlight Holography
Computational highlight holography converts 3D models into mechanical "holograms". Small grooves are milled into a surface, and each produces a reflected or refracted highlight that moves with correct binocular and motion parallax.
TOG Article: 147
Stereoscopic 3D Copy & Paste
This end-to-end system for 3D copy and paste handles occlusion and perspective change, and it preserves the stereo volume of copied objects.
TOG Article: 168
Spectral Sampling of Manifolds
This sampling method based on spectral analysis of manifolds results in faithful reconstructions, and it is efficient, out-of-core, feature-sensitive, intuitive to control, and simple to implement.
TOG Article: 145
Diffusion Maps for Edge-Aware Image Editing
This paper demonstrates the advantages of using diffusion distances instead of regular distances between pixel values in edge-aware image editing, and it analyzes efficient methods for computing such distances.
TOG Article: 174
Scalable Fluid Simulation Using Anisotropic Turbulence Particles
A novel, scalable method for simulating turbulent fluids. The method uses energy transport and an efficient particle representation to achieve accurate turbulent detail at interactive frame rates.
TOG Article: 162
Circularly Polarized Spherical Illumination Reflectometry
A novel method for surface reflectometry based on photographing a subject under a full-on spherical field of circularly polarized illumination and analysis of the resultant Stokes reflectance field.
TOG Article: 156
Multi-Resolution Isotropic Strain Limiting
A fast multi-resolution, isotropic strain-limiting method that is straightforward to implement, efficient to use, and applicable to a wide range of shell and solid materials.
TOG Article: 177
Unbiased, Adaptive Stochastic Sampling for Rendering Inhomogeneous Participating Media
This unbiased and adaptive sampling technique for generating scattering events accelerates rendering of highly inhomogeneous participating media inbyone to two orders of magnitude.
TOG Article: 181
Computer-Generated Residential Building Layouts
A method for automated generation of interior building layouts. The approach is based on the layout design process developed in architecture.
TOG Article: 176
Detail-Preserving Fully-Eulerian Interface Tracking Framework
This paper presents a new fully Eulerian interface tracking framework that preserves fine details of liquid.
TOG Article: 154
Real-Time Collision Culling of a Million Bodies on Graphics Processing Units
A very fast, parallel, broad-phase collision-culling algorithm that can deal with a million objects. The algorithm is integrated with real-time simulation of particle dynamics and rigid-body dynamics.
TOG Article: 146
Data-Driven Image Color Theme Enhancement
Photographers carefully conceive the color composition of their images to convey desired color themes. This paper presents a data-driven method for enhancing a desired color theme in an image.
TOG Article: 158
Automatic Generation of Destination Maps
A system for automatic generation of destination maps: navigational aids designed to show anyone within a region how to reach a small set of locations.
TOG Article: 150
Cone Carving for Surface Reconstruction
Visibility cones carve the ambient space of the shape from inside out to better approximate the signed distances to the shape near holes and infer correct surface topology for reconstruction.
TOG Article: 138
Motion Fields for Interactive Character Animation
A structureless representation of motion data enables intelligent characters with highly agile responses to user input and natural handling of arbitrary disturbances.
TOG Article: 144
A Progressive Error Estimation Framework for Photon Density Estimation
A first-error estimation framework for photon-density estimation methods that works under complex and general light transport configurations.
TOG Article: 148
MovieReshape: Tracking and Reshaping of Humans in Videos
A method for quick and easy manipulation of the body shape and proportions of a human actor in arbitrary video footage.
TOG Article: 149
Metric-Aware Processing of Spherical Imagery
An adapted finite-element system that supports intrinsic gradient-domain processing of spherical imagery.
TOG Article: 182
Context-Based Search for 3D Models
A context-based model search engine that uses information about the supporting scene a user is building to find good models.
TOG Article: 157
Animation Wrinkling: Augmenting Coarse Cloth Simulations With Realistic-Looking Wrinkles
Moving cloth exhibits dynamic, complex wrinkles. Existing wrinkling methods are computationally expensive and require significant user expertise. This alternative approach augments existing coarse-cloth animation with realistic-looking dynamic wrinkles.
TOG Article: 184
Style-Content Separation by Anisotropic Part Scales
This paper demonstrates co-analysis of a set of 3D objects to create novel instances derived from the set. The analysis is facilitated by style-content separation.
TOG Article: 172
Axial-Cones: Modeling Spherical Catadioptric Cameras for Wide-Angle Light Field Rendering
This novel geometric ray modeling for non-central spherical catadioptric cameras allows fast and exact wide-FOV lightfield rendering. The method enables perspective algorithms to be directly applied to catadioptric cameras.
TOG Article: 164
Optical Computing for Fast Light Transport Analysis
This paper shows how to efficiently perform numerical computations on a scene's unknown transport matrix (eigenvector analysis, low-rank approximation, inversion) by doing them partially in optics with projectors and cameras.
TOG Article: 161
Video Quality Assessment for Computer Graphics Applications
The proposed metric predicts the perceived quality of natural as well as rendered video sequences, even if the input videos have different dynamic ranges.
TOG Article: 151
Automatic Reconstruction of Tree Skeletal Structures From Point Clouds
An automatic approach to reconstructing tree skeletal structures from point clouds that are often noisy, incomplete, and have trees with overlapping crowns.
TOG Article: 165
Light Reallocation for High-Contrast Projection Using Analog Micromirror Arrays
This paper demonstrates a proof-of-concept projector with a secondary array of individually controllable analog micromirrors added to improve the contrast and peak brightness of conventional projectors by reallocating light.
TOG Article: 159
Resizing by Symmetry-Summarization
Understanding the symmetry content inside an image allows image resizing via summarization. This provides extra space for effective image resizing.
TOG Article: 142
Consistent Normal Interpolation
A simple modification of Phong normal interpolation that allows physically plausible reflections yet changes smoothly across the surface.
TOG Article: 153
Editing Operations for Irregular Vertices in Triangle Meshes
An interactive editing framework that provides control over the type, location, and number of irregular vertices in the input mesh.
TOG Article: 143
Combining Global and Local Virtual Lights for Detailed Glossy Illumination
This global-illumination solution for glossy inter-reflections handles the low-rank (dense) and high-rank (sparse) lighting components separately, using visibility clustering and a novel local-lights technique.
TOG Article: 178
A Hierarchical Volumetric Shadow Algorithm for Single Scattering
An incremental, hierarchical algorithm for rendering volumetric shadows in single-scattering participating media.
TOG Article: 141
A Practical Appearance Model for Dynamic Facial Color
This animatable appearance model for skin-color animation, based on real measurements of melanin and hemoglobin, is efficiently coupled with a geometric facial-animation rig.
TOG Article: 163
Content-Adaptive Parallax Barriers: Optimizing Dual-Layer 3D Displays Using Low-Rank Light Field Factorization
This method for optimizing automultiscopic dual-stacked LCDs proves that conventional parallax barriers only project rank-1 light fields and demonstrates higher-rank reconstructions using time-multiplexed masks, optimized for each frame.
TOG Article: 139
Video-Based Reconstruction of Animatable Human Characters
A new performance-capture approach that reconstructs a rigged fully animatable virtual double of a real person from multi-view video recordings.
TOG Article: 160
A Comparative Study of Image Retargeting
A comprehensive study and analysis of image-retargeting methods and human perception of resized images.
TOG Article: 185
Multi-Feature Matching of Fresco Fragments
This multiple-cue matching approach for reassembling fragments of archaeological artifacts improves current 3D matching algorithms by incorporating normal-based feature descriptors and reweighting features by importance.
TOG Article: 167
Anisotropic Blue Noise Sampling
Anisotropic blue noise sampling extends traditional isotropic dart throwing, relaxation, and Fourier-spectrum analysis techniques for anisotropic scenarios. Applications include stippling, re-meshing, rendering, and object placement.
Wednesday
15 December
6:00 PM - 8:00 PM
Technical Papers
Imaging Hardware
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 162
Circularly Polarized Spherical Illumination Reflectometry
A novel method for surface reflectometry based on photographing a subject under a full-on spherical field of circularly polarized illumination and analysis of the resultant Stokes reflectance field.
TOG Article: 164
Optical Computing for Fast Light Transport Analysis
This paper shows how to efficiently perform numerical computations on a scene's unknown transport matrix (eigenvector analysis, low-rank approximation, inversion) by doing them partially in optics with projectors and cameras.
TOG Article: 165
Light Reallocation for High-Contrast Projection Using Analog Micromirror Arrays
This paper demonstrates a proof-of-concept projector with a secondary array of individually controllable analog micromirrors added to improve the contrast and peak brightness of conventional projectors by reallocating light.
TOG Article: 163
Content-Adaptive Parallax Barriers: Optimizing Dual-Layer 3D Displays Using Low-Rank Light Field Factorization
This method for optimizing automultiscopic dual-stacked LCDs proves that conventional parallax barriers only project rank-1 light fields and demonstrates higher-rank reconstructions using time-multiplexed masks, optimized for each frame.
Friday
17 December
4:15 PM - 6:00 PM
Technical Papers
3D Modeling
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 183
Data-Driven Suggestions for Creativity Support in 3D Modeling
This paper introduces data-driven suggestions for 3D modeling. The approach computes and presents components that can augment the artist's current shape.
TOG Article: 181
Computer-Generated Residential Building Layouts
A method for automated generation of interior building layouts. The approach is based on the layout design process developed in architecture.
TOG Article: 182
Context-Based Search for 3D Models
A context-based model search engine that uses information about the supporting scene a user is building to find good models.
TOG Article: 184
Style-Content Separation by Anisotropic Part Scales
This paper demonstrates co-analysis of a set of 3D objects to create novel instances derived from the set. The analysis is facilitated by style-content separation.
TOG Article: 185
Multi-Feature Matching of Fresco Fragments
This multiple-cue matching approach for reassembling fragments of archaeological artifacts improves current 3D matching algorithms by incorporating normal-based feature descriptors and reweighting features by importance.
Saturday
18 December
4:15 PM - 6:30 PM
Technical Papers
Image & Video Editing
Room E1-E4

Presented in English / 영어로 발표 됨

TOG Article: 147
Stereoscopic 3D Copy & Paste
This end-to-end system for 3D copy and paste handles occlusion and perspective change, and it preserves the stereo volume of copied objects.
TOG Article: 145
Diffusion Maps for Edge-Aware Image Editing
This paper demonstrates the advantages of using diffusion distances instead of regular distances between pixel values in edge-aware image editing, and it analyzes efficient methods for computing such distances.
TOG Article: 146
Data-Driven Image Color Theme Enhancement
Photographers carefully conceive the color composition of their images to convey desired color themes. This paper presents a data-driven method for enhancing a desired color theme in an image.
TOG Article: 148
MovieReshape: Tracking and Reshaping of Humans in Videos
A method for quick and easy manipulation of the body shape and proportions of a human actor in arbitrary video footage.
TOG Article: 149
Metric-Aware Processing of Spherical Imagery
An adapted finite-element system that supports intrinsic gradient-domain processing of spherical imagery.
Thursday
16 December
4:15 PM - 6:30 PM
Technical Sketches
Education
Room 315

Presented in English / 영어로 발표 됨

Understanding Ohm's Law - Enlightenment Through Augmented Reality
A new application of augmented-reality technology in teaching the physics of electical circuits.
Virtual Heritage Production as a Tool in Education
Virtual heritage productions typically require many different fields of expertise, so it is a good match for interdisciplinary teamwork theory.
Visual Metaphors for Teaching Solar System and Gravity
Real-world visual metaphors that convey the concepts of the solar system and gravity to children.
Thursday
16 December
2:15 PM - 4:00 PM
Technical Sketches
Expressive Faces and Clothing
Room 308A

Presented in English / 영어로 발표 됨

Automated Target Selection for DrivenShape
This sketch presents an automated means to select targets for
DrivenShape. Targets are chosen to allow DrivenShape to
produce the lowest error in common contexts.
The Emotion Color Wheel: An Interface for Real-Time Facial Animation
The EmoCoW is an experimental color-coded interface for blend-shape animating of virtual characters in real time with only one hand and a six-axes input device.
A Hybrid Approach to Facial Rigging
This sketch presents a hybrid approach to facial rigging that uses
Pose Space Deformation to seamlessly combine both geometric
deformations and blendshapes.
Face Reality: Investigating the Uncanny Valley for Virtual Faces
An experiment to determine if changing the rendering style of a conversing virtual human alone can change how trustworthy the character is perceived to be.
Saturday
18 December
9:00 AM - 10:45 AM
Technical Sketches
Games
Room 308A

Presented in English / 영어로 발표 됨

Modeling Player Performance In Rhythm Games
A method for modeling skill level in a rhythm game by building probabilistic models of how well the player is able to match a technically perfect execution.
EDGE: An Easy Design Tool for Rapid Game Development
With EDGE, game designers without programming skills can make game events and effects.
Measuring Interest in Linear Single-Player FPS Games
This study measured attention levels to identify points of high player interest in linear single-player FPS games.
Integrating Lip-Synch Into Game Production Workflow: Sengoku BASARA 3
This skeetch describes integration of automated lip-synch (lip synchronization) into production of Sengoku BASARA 3, a PS3/Wii game by Capcom.
Thursday
16 December
9:00 AM - 10:45 AM
Technical Sketches
Geometry Capture and Reconstruction
Room 308A

Presented in English / 영어로 발표 됨

An Image Query-Based Approach for Urban Modeling
This method for reconstructing actual cityscapes uses pre-created texture and 3D models, and searches
suitable objects based on a photograph of buildings.
Pose-Invariant 3D Face Reconstruction From a Single Image
A novel method for 3D face reconstruction from only a single image, without requiring the image to be in a specific pose.
Face Models From Noisy 3D Cameras
A model-based approach to computing high-quality 3D face models from very noisy 3D data such as that obtained from time-of-flight cameras without user interaction.
A Correspondence-Matching Technique of Dense Checkerboard Pattern for One-Shot Geometry Acquisition
A rapid correspondence-matching technique for a dense and incomplete checkerboard pattern displayed by a projector-camera system for one-shot geometry acquisition.
Thursday
16 December
4:15 PM - 6:00 PM
Technical Sketches
Geometry Processing
Room 308A

Presented in English / 영어로 발표 됨

Hexagonal Global Parameterization of Arbitrary Surfaces
A new type of global surface parameterization that respects six-fold rotational symmetries in surfaces, with applications in texture and geometry-pattern synthesis as well as triangular remeshing.
Skeleton-Growing: A Vector-Field-Based 3D Curve-Skeleton Extraction Algorithm
Skeleton-growing is a 3D curve-skeleton extraction algorithm that can deliver a single reliable result without the threshold-adjusting process.
ProtoSphere: A GPU-Assisted Prototype-Guided Sphere-Packing Algorithm for Arbitrary Objects
A novel method for filling arbitrary objects very quickly and stably with sets of non-overlapping spheres.
Robustly Discovering Partial Rigid Symmetries on 3D Models
An iterative voting method to robustly discover partial rigid symmetries on 3D models, especially symmetries at small scales.
Thursday
16 December
2:15 PM - 4:00 PM
Technical Sketches
Image Editing
Room 308A

Presented in English / 영어로 발표 됨

Fast Local Color Transfer Via Dominant Colors Mapping
A more accurate local color-transfer method.
NinjaEdit: Simultaneous and Consistent Editing of an Unorganized Set of Photographs
A novel editing technique to apply visual effects to multiple photographs of a scene easily and simultaneously, maintaining their visual coherency with 3D reconstruction.
Fusion-Based Image and Video Decolorization
A novel decolorization method built on the principle of image fusion.
Layer-Based Single-Image Dehazing by Per-Pixel Haze Detection
A novel single-image dehazing technique built on a per-pixel haze-detection strategy.
Saturday
18 December
11:00 AM - 12:45 PM
Technical Sketches
Rendering and Textures
Room 315

Presented in English / 영어로 발표 됨

Texture Transfer Based on Continuous Structure of Texture Patches
A texture-transfer method that considers continuous structure of texture patches to express the continuous flow of Shodo (Chinese and Japanese calligraphy) art brushwork.
An Empirical Fur Shader
An empirical fur shader that can render the difference between animal fur structures. Human hair fibers can also be handled in the same framework.
Point-Based Hair Global Illumination
A point based representation was extensively used on "Tangled" to generate occlusion and indirect illumination involving the characters' hair. This sketch describes how this was achieved in reasonable rendering times.
Direct Ray Tracing of Phong Tessellation
A summary of the details of direct ray tracing of Phong Tessellation, which enables rendering of smooth surfaces in a simple and robust way.
Friday
17 December
9:00 AM - 10:45 AM
Technical Sketches
Production and New Media
Room 308A

Presented in English / 영어로 발표 됨

Simulation-Aided Performance: Behind The Coils Of Slinky Dog in "Toy Story 3"
Summary of the collaborative work between simulation technical directors and animators for Slinky Dog in "Toy Story 3".
Simulating Drools and Snots for Bulls in "Knight and Day"
A set of techniques used to produce drool effects for bulls in the "Knight and Day" movie production.
MobiRT: An Implementation of OpenGL ES-Based CPU-GPU Hybrid Ray Tracer for Mobile Devices
Implementation of an OpenGL ES-based CPU-GPU hybrid ray trace, the first demonstration of full-Whitted ray tracing in dynamic scenes using OpenGL ES.
Blue Mars Chronicles: Building for Millions
Insights and guidelines on how to maintain productive relationships with 3D content developers of the online virtual world Blue Mars.
Saturday
18 December
2:15 PM - 4:00 PM
Technical Sketches Fast Forward
Technical Sketches Fast Forward Session
Room E5

Presented in English / 영어로 발표 됨

Displaced Subdivision Surfaces of Animated Meshes
A technique for extraction of a series of displaced subdivision surfaces from an existing animated mesh.
Synchronized Partial-Body Motion Graphs
An automatic method to construct a graph that specifies transitions and correlations between partial-body motions so as to increase the connectivity and the reusability of the graphs.
Modeling Player Performance In Rhythm Games
A method for modeling skill level in a rhythm game by building probabilistic models of how well the player is able to match a technically perfect execution.
Fast Local Color Transfer Via Dominant Colors Mapping
A more accurate local color-transfer method.
High-Frequency-Aware PIC/FLIP in Liquid Animation
A simple extension to PIC/FLIP (Particle-in-Cell/Fluid-Implicit-Particle) for animating liquid with enhanced behaviors such as pushing or eddying.
Automatic Architecture Model Generation Based on Object Hierarchy
A novel framework for generating an explicit architecture model from scanned points of an existing
architecture.
Shading-Interval Constraints for Normal Map Editing
A new paint-based approach to editing a normal map according to the intended shading. It is formulated as a quadratic optmization with interval constraints on shading.
Simulation-Aided Performance: Behind The Coils Of Slinky Dog in "Toy Story 3"
Summary of the collaborative work between simulation technical directors and animators for Slinky Dog in "Toy Story 3".
Hexagonal Global Parameterization of Arbitrary Surfaces
A new type of global surface parameterization that respects six-fold rotational symmetries in surfaces, with applications in texture and geometry-pattern synthesis as well as triangular remeshing.
Texture Transfer Based on Continuous Structure of Texture Patches
A texture-transfer method that considers continuous structure of texture patches to express the continuous flow of Shodo (Chinese and Japanese calligraphy) art brushwork.
Real-Time Stereo Visual Hull Rendering using a Multi-GPU-accelerated Pipeline
A novel real-time, image-based visual hull-rendering pipeline that adopts a single PC with multiple GPUs and renders stereo images of the object at 30~40 fps.
Ordered Depth-First Layouts for Ray Tracing
In this ordered depth-first tree layout, a child that has a larger surface area is stored next to its parent, so parent-child localities can be maximized.
Real-Time Controlled Metamorphosis of Animated Meshes Using Polygonal-Functional Hybrids
This approach allows production of metamorphosing transitions between animated meshes of arbitrary topology in real time, using both the meshes and the animated skeletons of the objects.
Stable and Efficient Differential Inverse Kinematics
This method combines ideas from two differential inverse kinematics algorithms to produce a new approach that is both efficient and free from instability.
An Empirical Fur Shader
An empirical fur shader that can render the difference between animal fur structures. Human hair fibers can also be handled in the same framework.
Parallel Progressive Photon Mapping on GPUs
A GPU implementation of progressive photon mapping. The main idea is a new data-parallel progressive radiance estimation algorithm, including data-parallel construction of photon maps.
An Image Query-Based Approach for Urban Modeling
This method for reconstructing actual cityscapes uses pre-created texture and 3D models, and searches
suitable objects based on a photograph of buildings.
A Real-Time Computer Model for Wind-Driven Fallen Snow
A new modeling method for the appearance of accumulated snow formed by snow-drift near obstacles in real time.
Derivation of Dance Similarity From Balance Characteristics
A novel similarity measure for motion-capture data streams of dance movements. The method includes balance, because balance depends on the context of motion.
EDGE: An Easy Design Tool for Rapid Game Development
With EDGE, game designers without programming skills can make game events and effects.
Skeleton-Growing: A Vector-Field-Based 3D Curve-Skeleton Extraction Algorithm
Skeleton-growing is a 3D curve-skeleton extraction algorithm that can deliver a single reliable result without the threshold-adjusting process.
Automated Target Selection for DrivenShape
This sketch presents an automated means to select targets for
DrivenShape. Targets are chosen to allow DrivenShape to
produce the lowest error in common contexts.
Point-Based Hair Global Illumination
A point based representation was extensively used on "Tangled" to generate occlusion and indirect illumination involving the characters' hair. This sketch describes how this was achieved in reasonable rendering times.
Simulating Drools and Snots for Bulls in "Knight and Day"
A set of techniques used to produce drool effects for bulls in the "Knight and Day" movie production.
Direct Ray Tracing of Phong Tessellation
A summary of the details of direct ray tracing of Phong Tessellation, which enables rendering of smooth surfaces in a simple and robust way.
Space-Time Blending With Improved User Control in Real Time
Improving the original space-time blending technique to provide users with a set of more intuitive controls in real-time applications.
MobiRT: An Implementation of OpenGL ES-Based CPU-GPU Hybrid Ray Tracer for Mobile Devices
Implementation of an OpenGL ES-based CPU-GPU hybrid ray trace, the first demonstration of full-Whitted ray tracing in dynamic scenes using OpenGL ES.
Virtual Heritage Production as a Tool in Education
Virtual heritage productions typically require many different fields of expertise, so it is a good match for interdisciplinary teamwork theory.
The Emotion Color Wheel: An Interface for Real-Time Facial Animation
The EmoCoW is an experimental color-coded interface for blend-shape animating of virtual characters in real time with only one hand and a six-axes input device.
Sub-100 Grams Ungrounded Haptic Device for 14-g Impact Simulation
An untethered, push-pull, spring-less, solenoid-based handheld device that simulates 14g impacts in mid-air, for simulating ball-racket collisions in a tennis simulator.
Visual Metaphors for Teaching Solar System and Gravity
Real-world visual metaphors that convey the concepts of the solar system and gravity to children.
Single-Shot Photometric Stereo by Spectral Multiplexing
Generalizing three-color photometric stereo to multiple color channels, yielding both a normal map and a full-color reflectance map in a single shot, using off-the-shelf parts only.
Pose-Invariant 3D Face Reconstruction From a Single Image
A novel method for 3D face reconstruction from only a single image, without requiring the image to be in a specific pose.
Interactive Voxelized Epipolar Shadow Volumes
A new visibility sampling in epipolar space that can be efficiently computed via a standard parallel scan. This allows shadow rendering in participating media at up to 300 fps.
Minimal Image Sets for Robust Spherical Gradient Photometric Stereo
A new method for reducing data-capture requirements for accurate face-shape recovery.
Perceptual Evaluation of Human Animation Timewarping
This perceptual evaluation of motion timewarping, a common editing method for motion capture data, finds a significant difference between speeding up and slowing down the motions.
Electrostatic Dynamics Interaction for Cloth
By simulating a new external force, this method implements electrostatic adherence behaviors between textile and objects. With Coulomb's law, draping and balloon floating influenced by electrostatic field are realistically illustrated.
Understanding Ohm's Law - Enlightenment Through Augmented Reality
A new application of augmented-reality technology in teaching the physics of electical circuits.
Measuring Interest in Linear Single-Player FPS Games
This study measured attention levels to identify points of high player interest in linear single-player FPS games.
Free-Form Polarized Spherical Illumination Reflectometry
A lightweight in-situ acquisition system for per-pixel reflectance parameters, such as diffuse and specular albedo, specular roughness, and surface orientation.
ProtoSphere: A GPU-Assisted Prototype-Guided Sphere-Packing Algorithm for Arbitrary Objects
A novel method for filling arbitrary objects very quickly and stably with sets of non-overlapping spheres.
Blue Mars Chronicles: Building for Millions
Insights and guidelines on how to maintain productive relationships with 3D content developers of the online virtual world Blue Mars.
NinjaEdit: Simultaneous and Consistent Editing of an Unorganized Set of Photographs
A novel editing technique to apply visual effects to multiple photographs of a scene easily and simultaneously, maintaining their visual coherency with 3D reconstruction.
Integrating Lip-Synch Into Game Production Workflow: Sengoku BASARA 3
This skeetch describes integration of automated lip-synch (lip synchronization) into production of Sengoku BASARA 3, a PS3/Wii game by Capcom.
Fusion-Based Image and Video Decolorization
A novel decolorization method built on the principle of image fusion.
Enhanced Interactive Gaming by Blending Full-Body Tracking and Gesture Recognition
A framework that enhances motion-capture tracking data by seamlessly blending it with predefined animations in real time. The process is triggered by a unique gesture-recognition system.
Layer-Based Single-Image Dehazing by Per-Pixel Haze Detection
A novel single-image dehazing technique built on a per-pixel haze-detection strategy.
OtoMushi: Touching Sound
OtoMushi displays sound samples as insects, allowing for quick exploration, mixing, and playback of a collection of sounds. Scratching the insects creates a similar effect on the sounds.
Face Models From Noisy 3D Cameras
A model-based approach to computing high-quality 3D face models from very noisy 3D data such as that obtained from time-of-flight cameras without user interaction.
A Hybrid Approach to Facial Rigging
This sketch presents a hybrid approach to facial rigging that uses
Pose Space Deformation to seamlessly combine both geometric
deformations and blendshapes.
A Correspondence-Matching Technique of Dense Checkerboard Pattern for One-Shot Geometry Acquisition
A rapid correspondence-matching technique for a dense and incomplete checkerboard pattern displayed by a projector-camera system for one-shot geometry acquisition.
Face Reality: Investigating the Uncanny Valley for Virtual Faces
An experiment to determine if changing the rendering style of a conversing virtual human alone can change how trustworthy the character is perceived to be.
PETICA: An Interactive Painting Tool With 3D Geometrical Brushes
Interactive painting software, PETICA, that enables users to freely design 3D shapes and attributes to create digital painting brushes and paint pictures with these brushes.
Elastic Rod Simulation by Chain-Shape Matching with Twisting Effect
A simple deformation model for handling the dynamics of bending, stretching, and twisting of elastic rods. Also: segment-based collision handling for complex collisions of the elastic rods.
Robustly Discovering Partial Rigid Symmetries on 3D Models
An iterative voting method to robustly discover partial rigid symmetries on 3D models, especially symmetries at small scales.
Wednesday
15 December
3:30 PM - 5:15 PM
Technical Sketches
Motion Editing and Control
Room 315

Presented in English / 영어로 발표 됨

Synchronized Partial-Body Motion Graphs
An automatic method to construct a graph that specifies transitions and correlations between partial-body motions so as to increase the connectivity and the reusability of the graphs.
Stable and Efficient Differential Inverse Kinematics
This method combines ideas from two differential inverse kinematics algorithms to produce a new approach that is both efficient and free from instability.
Derivation of Dance Similarity From Balance Characteristics
A novel similarity measure for motion-capture data streams of dance movements. The method includes balance, because balance depends on the context of motion.
Perceptual Evaluation of Human Animation Timewarping
This perceptual evaluation of motion timewarping, a common editing method for motion capture data, finds a significant difference between speeding up and slowing down the motions.
Friday
17 December
4:15 PM - 6:00 PM
Technical Sketches
Physics and Natural Phenomena
Room 308A

Presented in English / 영어로 발표 됨

High-Frequency-Aware PIC/FLIP in Liquid Animation
A simple extension to PIC/FLIP (Particle-in-Cell/Fluid-Implicit-Particle) for animating liquid with enhanced behaviors such as pushing or eddying.
A Real-Time Computer Model for Wind-Driven Fallen Snow
A new modeling method for the appearance of accumulated snow formed by snow-drift near obstacles in real time.
Electrostatic Dynamics Interaction for Cloth
By simulating a new external force, this method implements electrostatic adherence behaviors between textile and objects. With Coulomb's law, draping and balloon floating influenced by electrostatic field are realistically illustrated.
Elastic Rod Simulation by Chain-Shape Matching with Twisting Effect
A simple deformation model for handling the dynamics of bending, stretching, and twisting of elastic rods. Also: segment-based collision handling for complex collisions of the elastic rods.
Friday
17 December
2:15 PM - 4:00 PM
Technical Sketches
Interaction and Virtual Reality
Room 308A

Presented in English / 영어로 발표 됨

Sub-100 Grams Ungrounded Haptic Device for 14-g Impact Simulation
An untethered, push-pull, spring-less, solenoid-based handheld device that simulates 14g impacts in mid-air, for simulating ball-racket collisions in a tennis simulator.
Enhanced Interactive Gaming by Blending Full-Body Tracking and Gesture Recognition
A framework that enhances motion-capture tracking data by seamlessly blending it with predefined animations in real time. The process is triggered by a unique gesture-recognition system.
OtoMushi: Touching Sound
OtoMushi displays sound samples as insects, allowing for quick exploration, mixing, and playback of a collection of sounds. Scratching the insects creates a similar effect on the sounds.
PETICA: An Interactive Painting Tool With 3D Geometrical Brushes
Interactive painting software, PETICA, that enables users to freely design 3D shapes and attributes to create digital painting brushes and paint pictures with these brushes.
Friday
17 December
4:15 PM - 6:00 PM
Technical Sketches
Interactive Rendering
Room 315

Presented in English / 영어로 발표 됨

Real-Time Stereo Visual Hull Rendering using a Multi-GPU-accelerated Pipeline
A novel real-time, image-based visual hull-rendering pipeline that adopts a single PC with multiple GPUs and renders stereo images of the object at 30~40 fps.
Ordered Depth-First Layouts for Ray Tracing
In this ordered depth-first tree layout, a child that has a larger surface area is stored next to its parent, so parent-child localities can be maximized.
Parallel Progressive Photon Mapping on GPUs
A GPU implementation of progressive photon mapping. The main idea is a new data-parallel progressive radiance estimation algorithm, including data-parallel construction of photon maps.
Interactive Voxelized Epipolar Shadow Volumes
A new visibility sampling in epipolar space that can be efficiently computed via a standard parallel scan. This allows shadow rendering in participating media at up to 300 fps.
Saturday
18 December
4:15 PM - 6:00 PM
Technical Sketches
Animated Meshes and Architecture
Room 315

Presented in English / 영어로 발표 됨

Displaced Subdivision Surfaces of Animated Meshes
A technique for extraction of a series of displaced subdivision surfaces from an existing animated mesh.
Automatic Architecture Model Generation Based on Object Hierarchy
A novel framework for generating an explicit architecture model from scanned points of an existing
architecture.
Real-Time Controlled Metamorphosis of Animated Meshes Using Polygonal-Functional Hybrids
This approach allows production of metamorphosing transitions between animated meshes of arbitrary topology in real time, using both the meshes and the animated skeletons of the objects.
Space-Time Blending With Improved User Control in Real Time
Improving the original space-time blending technique to provide users with a set of more intuitive controls in real-time applications.
Saturday
18 December
9:00 AM - 10:45 AM