Learning hatching for pen-and-ink illustration of surfaces

Authors:
Evangelos Kalogerakis;Derek Nowrouzezahrai;Simon Breslav;Aaron Hertzmann
Affiliations:
University of Toronto and Stanford University;University of Toronto, Disney Research Zurich, and University of Montreal;University of Toronto and Autodesk Research;University of Toronto
Venue:
ACM Transactions on Graphics (TOG)
Year:
2012

Citing 38
Cited 4

Comprehensible rendering of 3-D shapes

SIGGRAPH '90 Proceedings of the 17th annual conference on Computer graphics and interactive techniques
Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Computer-generated pen-and-ink illustration

SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Interactive pen-and-ink illustration

SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Applications of irradiance tensors to the simulation of non-Lambertian phenomena

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Image-guided streamline placement

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Rendering parametric surfaces in pen and ink

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Illustrating smooth surfaces

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Topology matching for fully automatic similarity estimation of 3D shapes

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Image analogies

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Real-time hatching

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hatching by example: a statistical approach

NPAR '02 Proceedings of the 2nd international symposium on Non-photorealistic animation and rendering
Precomputed radiance transfer for real-time rendering in dynamic, low-frequency lighting environments

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
WYSIWYG NPR: drawing strokes directly on 3D models

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Curve analogies

EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Learning style translation for the lines of a drawing

ACM Transactions on Graphics (TOG)
Line Art Illustrations of Parametric and Implicit Forms

IEEE Transactions on Visualization and Computer Graphics
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Constrained K-means Clustering with Background Knowledge

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Sharing Visual Features for Multiclass and Multiview Object Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Isophote distance: a shading approach to artistic stroke thickness

Proceedings of the 5th international symposium on Non-photorealistic animation and rendering
Highlight lines for conveying shape

Proceedings of the 5th international symposium on Non-photorealistic animation and rendering
Apparent ridges for line drawing

ACM SIGGRAPH 2007 papers
Rotational symmetry field design on surfaces

ACM SIGGRAPH 2007 papers
Folding meshes: hierarchical mesh segmentation based on planar symmetry

SGP '06 Proceedings of the fourth Eurographics symposium on Geometry processing
Where do people draw lines?

ACM SIGGRAPH 2008 papers
Line-art illustration of dynamic and specular surfaces

ACM SIGGRAPH Asia 2008 papers
Data-driven curvature for real-time line drawing of dynamic scenes

ACM Transactions on Graphics (TOG)
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

International Journal of Computer Vision
Stippling by example

Proceedings of the 7th International Symposium on Non-Photorealistic Animation and Rendering
From image parsing to painterly rendering

ACM Transactions on Graphics (TOG)
Learning 3D mesh segmentation and labeling

ACM SIGGRAPH 2010 papers
Contextual Part Analogies in 3D Objects

International Journal of Computer Vision
Automated hedcut illustration using isophotes

SG'10 Proceedings of the 10th international conference on Smart graphics
Suggestive hatching

Computational Aesthetics'10 Proceedings of the Sixth international conference on Computational Aesthetics in Graphics, Visualization and Imaging
Texture transfer using geometry correlation

EGSR'06 Proceedings of the 17th Eurographics conference on Rendering Techniques

Technical Section: Interactive example-based hatching

Computers and Graphics
Style and abstraction in portrait sketching

ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Authoring and animating painterly characters

ACM Transactions on Graphics (TOG)
Real-time rendering of water surfaces with cartography-oriented design

Proceedings of the Symposium on Computational Aesthetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

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-hatching, or no strokes), stroke orientation, spacing, intensity, length, and thickness. A mapping is learned from input geometric, contextual, and shading features of the 3D object to these hatching properties, using classification, regression, and clustering techniques. Then, a new illustration can be generated in the artist's style, as follows. First, given a new view of a 3D object, the learned mapping is applied to synthesize target stroke properties for each pixel. A new illustration is then generated by synthesizing hatching strokes according to the target properties.