Search For:

Displaying 1-43 out of 43 total
Feature-based locomotion controllers
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa
Issue Date:July 2010
pp. 1-10
This paper introduces an approach to control of physics-based characters based on high-level features of movement, such as center-of-mass, angular momentum, and end-effectors. Objective terms are used to control each feature, and are combined by a prioriti...
     
Learning 3D mesh segmentation and labeling
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Evangelos Kalogerakis, Karan Singh, Aaron Hertzmann, Evangelos Kalogerakis, Karan Singh, Aaron Hertzmann, Evangelos Kalogerakis, Karan Singh, Aaron Hertzmann, Evangelos Kalogerakis, Karan Singh
Issue Date:July 2010
pp. 1-10
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes. An objective function is formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms betwee...
     
Optimizing walking controllers for uncertain inputs and environments
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:July 2010
pp. 1-10
We introduce methods for optimizing physics-based walking controllers for robustness to uncertainty. Many unknown factors, such as external forces, control torques, and user control inputs, cannot be known in advance and must be treated as uncertain. These...
     
Robust physics-based locomotion using low-dimensional planning
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa, Aaron Hertzmann, Igor Mordatch, Martin de Lasa
Issue Date:July 2010
pp. 1-10
This paper presents a physics-based locomotion controller based on online planning. At each time-step, a planner optimizes locomotion over multiple phases of gait. Stance dynamics are modeled using a simplified Spring-Load Inverted (SLIP) model, while flig...
     
AniPaint: Interactive Painterly Animation from Video
Found in: IEEE Transactions on Visualization and Computer Graphics
By Peter O'Donovan,Aaron Hertzmann
Issue Date:March 2012
pp. 475-487
This paper presents an interactive system for creating painterly animation from video sequences. Previous approaches to painterly animation typically emphasize either purely automatic stroke synthesis or purely manual stroke keyframing. Our system supports...
 
A Survey of Stroke-Based Rendering
Found in: IEEE Computer Graphics and Applications
By Aaron Hertzmann
Issue Date:July 2003
pp. 70-81
<p>This tutorial describes stroke-based rendering (SBR), an automatic approach to creating nonphotorealistic imagery by placing discrete elements called strokes, such as paint strokes or stipples. Many SBR algorithms and styles have been proposed, in...
 
Shape and Materials by Example: A Photometric Stereo Approach
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Aaron Hertzmann, Steven M. Seitz
Issue Date:June 2003
pp. 533
This paper presents a technique for computing the geometry of objects with general reflectance properties from images. For surfaces with varying material properties, a full segmentation into different material types is also computed. It is assumed that the...
 
Optimizing walking controllers
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang, Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:December 2009
pp. 1-2
This paper describes a method for optimizing the parameters of a physics-based controller for full-body, 3D walking. A modified version of the SIMBICON controller [Yin et al. 2007] is optimized for characters of varying body shape, walking speed and step l...
     
Physics-Based Characters
Found in: IEEE Computer Graphics and Applications
By Aaron Hertzmann, Victor Zordan
Issue Date:July 2011
pp. 20-21
A new generation of physics-based animation approaches are beginning to emerge that are robust and maintain a standard of visual quality as high as data-driven synthesis. And even with the holy grail of control principles that describe human motion still a...
 
Shape and Spatially-Varying BRDFs from Photometric Stereo
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Dan B Goldman, Brian Curless, Aaron Hertzmann, Steven M. Seitz
Issue Date:June 2010
pp. 1060-1071
This paper describes a photometric stereo method designed for surfaces with spatially-varying BRDFs, including surfaces with both varying diffuse and specular properties. Our optimization-based method builds on the observation that most objects are compose...
 
Correction to
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jack M. Wang, David J. Fleet, Aaron Hertzmann
Issue Date:June 2008
pp. 1118
No summary available.
 
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lorenzo Torresani, Aaron Hertzmann, Chris Bregler
Issue Date:May 2008
pp. 878-892
This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instan...
 
Gaussian Process Dynamical Models for Human Motion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jack M. Wang, David J. Fleet, Aaron Hertzmann
Issue Date:February 2008
pp. 283-298
We introduce Gaussian process dynamical models (GPDM) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensionalmotion capture data. A GPDM is a latent variable model. It comprises a low-dimensio...
 
Physics-Based Person Tracking Using Simplified Lower-Body Dynamics
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Marcus A. Brubaker, David J. Fleet, Aaron Hertzmann
Issue Date:June 2007
pp. 1-8
We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact, generalizes naturally to...
 
Shape and Spatially-Varying BRDFs from Photometric Stereo
Found in: Computer Vision, IEEE International Conference on
By Dan B. Goldman, Brian Curless, Aaron Hertzmann, Steven M. Seitz
Issue Date:October 2005
pp. 341-348
This paper describes a photometric stereo method designed for surfaces with spatially-varying BRDFs, including surfaces with both varying diffuse and specular properties. Our method builds on the observation that most objects are composed of a small number...
 
Priors for People Tracking from Small Training Sets
Found in: Computer Vision, IEEE International Conference on
By Raquel Urtasun, David J. Fleet, Aaron Hertzmann, Pascal Fua
Issue Date:October 2005
pp. 403-410
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density fu...
 
Example-Based Photometric Stereo: Shape Reconstruction with General, Varying BRDFs
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Aaron Hertzmann, Steven M. Seitz
Issue Date:August 2005
pp. 1254-1264
This paper presents a technique for computing the geometry of objects with general reflectance properties from images. For surfaces with varying material properties, a full segmentation into different material types is also computed. It is assumed that the...
 
Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo
Found in: Computer Vision, IEEE International Conference on
By Li Zhang, Brian Curless, Aaron Hertzmann, Steven M. Seitz
Issue Date:October 2003
pp. 618
This paper presents an algorithm for computing optical flow, shape, motion, lighting, and albedo from an image sequence of a rigidly-moving Lambertian object under distant illumination. The problem is formulated in a manner that subsumes structure from mot...
 
Machine Learning for Computer Graphics: A Manifesto and Tutorial
Found in: Computer Graphics and Applications, Pacific Conference on
By Aaron Hertzmann
Issue Date:October 2003
pp. 22
I argue that computer graphics can bene.t from a deeper use of machine learning techniques. I give an overview of what learning has to offer the graphics community, with an emphasis on Bayesian techniques. I also attempt to address some misconceptions abou...
 
Paint By Relaxation
Found in: Computer Graphics International Conference
By Aaron Hertzmann
Issue Date:July 2001
pp. 0047
Abstract: We use relaxation to produce painted imagery from images and video. An energy function is first specified; we then search for a painting with minimal energy. The appeal of this strategy is that, ideally, we need only specify what we want, not how...
 
Learning Layouts for Single-PageGraphic Designs
Found in: IEEE Transactions on Visualization and Computer Graphics
By Peter ODonovan,Aseem Agarwala,Aaron Hertzmann
Issue Date:August 2014
pp. 1200-1213
This paper presents an approach for automatically creating graphic design layouts using a new energy-based model derived from design principles. The model includes several new algorithms for analyzing graphic designs, including the prediction of perceived ...
   
Computing smooth surface contours with accurate topology
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Michael Kass, Pierre Bénard
Issue Date:March 2014
pp. 1-21
This article introduces a method for accurately computing the visible contours of a smooth 3D surface for stylization. This is a surprisingly difficult problem, and previous methods are prone to topological errors, such as gaps in the outline. Our approach...
     
Learning hatching for pen-and-ink illustration of surfaces
Found in: ACM Transactions on Graphics (TOG)
By Evangelos Kalogerakis, Aaron Hertzmann, Derek Nowrouzezahrai, Simon Breslav
Issue Date:January 2012
pp. 1-17
This article presents an algorithm for learning hatching styles from line drawings. An artist draws a single hatching illustration of a 3D object. Her strokes are analyzed to extract the following per-pixel properties: hatching level (hatching, cross-hatch...
     
Color compatibility from large datasets
Found in: ACM SIGGRAPH 2011 papers (SIGGRAPH '11)
By Aaron Hertzmann, Aseem Agarwala, Peter O'Donovan
Issue Date:August 2011
pp. 287-294
This paper studies color compatibility theories using large datasets, and develops new tools for choosing colors. There are three parts to this work. First, using on-line datasets, we test new and existing theories of human color preferences. For example, ...
     
Color compatibility from large datasets
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Aseem Agarwala, Peter O'Donovan
Issue Date:July 2011
pp. 1-33
This paper studies color compatibility theories using large datasets, and develops new tools for choosing colors. There are three parts to this work. First, using on-line datasets, we test new and existing theories of human color preferences. For example, ...
     
Feature-based locomotion controllers
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Aaron Hertzmann, Igor Mordatch, Martin de Lasa
Issue Date:July 2010
pp. 10-18
This paper introduces an approach to control of physics-based characters based on high-level features of movement, such as center-of-mass, angular momentum, and end-effectors. Objective terms are used to control each feature, and are combined by a prioriti...
     
Learning 3D mesh segmentation and labeling
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Aaron Hertzmann, Evangelos Kalogerakis, Karan Singh
Issue Date:July 2010
pp. 10-18
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes. An objective function is formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms betwee...
     
Optimizing walking controllers for uncertain inputs and environments
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:July 2010
pp. 10-18
We introduce methods for optimizing physics-based walking controllers for robustness to uncertainty. Many unknown factors, such as external forces, control torques, and user control inputs, cannot be known in advance and must be treated as uncertain. These...
     
Robust physics-based locomotion using low-dimensional planning
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Aaron Hertzmann, Igor Mordatch, Martin de Lasa
Issue Date:July 2010
pp. 10-18
This paper presents a physics-based locomotion controller based on online planning. At each time-step, a planner optimizes locomotion over multiple phases of gait. Stance dynamics are modeled using a simplified Spring-Load Inverted (SLIP) model, while flig...
     
Optimizing walking controllers
Found in: ACM SIGGRAPH Asia 2009 papers (SIGGRAPH Asia '09)
By Aaron Hertzmann, David J. Fleet, Jack M. Wang
Issue Date:December 2009
pp. 1-6
This paper describes a method for optimizing the parameters of a physics-based controller for full-body, 3D walking. A modified version of the SIMBICON controller [Yin et al. 2007] is optimized for characters of varying body shape, walking speed and step l...
     
Realistic human body movement for emotional expressiveness
Found in: ACM SIGGRAPH 2009 Courses (SIGGRAPH '09)
By Aaron Hertzmann, Carol O'Sullivan, Ken Perlin
Issue Date:August 2009
pp. 1-27
Humans express their emotions in many ways, in particular through face, eye, and body motion. So creators of virtual humans strive to convincingly depict emotional movements using a variety of methods.This course focuses on the use of realistic human body ...
     
Data-driven curvature for real-time line drawing of dynamic scenes
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Derek Nowrouzezahrai, Evangelos Kalogerakis, James Mccrae, Karan Singh, Patricio Simari
Issue Date:January 2009
pp. 1-13
This article presents a method for real-time line drawing of deforming objects. Object-space line drawing algorithms for many types of curves, including suggestive contours, highlights, ridges, and valleys, rely on surface curvature and curvature derivativ...
     
Isophote distance: a shading approach to artistic stroke thickness
Found in: Proceedings of the 5th international symposium on Non-photorealistic animation and rendering (NPAR '07)
By Aaron Hertzmann, Ian Vollick, Todd Goodwin
Issue Date:August 2007
pp. 53-62
This paper presents an approach for determining stroke thickness in computer-generated illustrations of smooth surfaces. We assume that dark strokes are drawn to approximate the dark regions of the shaded surface. This assumption leads to a simple formula ...
     
Removing camera shake from a single photograph: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Aaron Hertzmann, Barun Singh, Rob Fergus, Sam T. Roweis, William T. Freeman
Issue Date:July 2006
pp. 36-es
Camera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency-domain constraints on images, or overly simplified parametric forms for the motion path during ca...
     
Removing camera shake from a single photograph: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Aaron Hertzmann, Barun Singh, Rob Fergus, Sam T. Roweis, William T. Freeman
Issue Date:July 2006
pp. 36-es
Camera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency-domain constraints on images, or overly simplified parametric forms for the motion path during ca...
     
Introduction to Bayesian learning
Found in: Proceedings of the conference on SIGGRAPH 2004 course notes (GRAPH '04)
By Aaron Hertzmann
Issue Date:August 2004
pp. 22-es
Sophisticated computer graphics applications require complex models of appearance, motion, natural phenomena, and even artistic style. Such models are often difficult or impossible to design by hand. Recent research demonstrates that, instead, we can "lear...
     
Keyframe-based tracking for rotoscoping and animation
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Aseem Agarwala, David H. Salesin, Steven M. Seitz
Issue Date:August 2004
pp. 584-591
We describe a new approach to rotoscoping --- the process of tracking contours in a video sequence --- that combines computer vision with user interaction. In order to track contours in video, the user specifies curves in two or more frames; these curves a...
     
Style-based inverse kinematics
Found in: ACM Transactions on Graphics (TOG)
By Aaron Hertzmann, Keith Grochow, Steven L. Martin, Zoran Popovic
Issue Date:August 2004
pp. 522-531
This paper presents an inverse kinematics system based on a learned model of human poses. Given a set of constraints, our system can produce the most likely pose satisfying those constraints, in real-time. Training the model on different input data leads t...
     
Shape analogies
Found in: ACM SIGGRAPH 2002 conference abstracts and applications (SIGGRAPH '02)
By Aaron Hertzmann, Brian Curless, Nuria Oliver, Steven M. Seitz
Issue Date:July 2002
pp. 247-247
This sketch presents "Shape Analogies," a method for learning line styles from examples. With this approach, an artist or end-user simply draws in the desired style; the system analyzes the drawings and generates new imagery in the same style. For example,...
     
Fast paint texture
Found in: Proceedings of the second international symposium on Non-photorealistic animation and rendering (NPAR '02)
By Aaron Hertzmann
Issue Date:June 2002
pp. 91-ff
We present a technique for simulating the physical appearance of paint strokes under lighting. This technique is easy-to-implement and very fast, yet produces realistic results. The system processes a painting composed of a list of brush strokes. A height ...
     
Image analogies
Found in: Proceedings of the 28th annual conference on Computer graphics and interactive techniques (SIGGRAPH '01)
By Aaron Hertzmann, Brian Curless, Charles E. Jacobs, David H. Salesin, Nuria Oliver
Issue Date:August 2001
pp. 327-340
This paper describes a new framework for processing images by example, called “image analogies.” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “filtered” version of th...
     
Painterly rendering for video and interaction
Found in: Proceedings of the first international symposium on Non-photorealistic animation and rendering (NPAR '00)
By Aaron Hertzmann, Ken Perlin
Issue Date:June 2000
pp. 7-12
Multicast avoids sending repeated packets over the same network links and thus offers the promise of supporting multimedia streaming over wide-area networks. Previously, two opposite multicast schemes -- forward-path forwarding and reverse-path forwarding ...
     
Painterly rendering with curved brush strokes of multiple sizes
Found in: Proceedings of the 25th annual conference on Computer graphics and interactive techniques (SIGGRAPH '98)
By Aaron Hertzmann
Issue Date:July 1998
pp. 453-460
This paper describes a physically-based rendering system tailored to the demands of lighting design and architecture. The simulation uses a light-backwards ray-tracing method with extensions to efficiently solve the rendering equation under most conditions...
     
 1