Research Interests: My research deals with the development of computer graphics techniques that enhance human creativity and automate complex visual content processing tasks for novice users, scientists and artists. I am particularly interested in developing machine learning algorithms for 3D shape analysis and synthesis. I am excited to develop algorithms and tools that allow users to quickly and easily create, acquire, texture, customize, animate, and artistically render three-dimensional content for virtual environments, computer games, computer-animated films, architecture, computer-aided design, information visualization, and medical applications.

Short bio: I joined the Department of Computer Science at the University of Massachusetts in September 2012. I obtained my PhD from the department of Computer Science, University of Toronto in September 2010. I was co-supervised by Aaron Hertzmann and Karan Singh. I was a postdoctoral researcher in the Computer Graphics lab of Stanford University from September 2010 to August 2012. I graduated from the department of Electrical and Computer Engineering, Technical University of Crete in August 2005.

A Probabilistic Model for Component-Based Shape Synthesis
Evangelos Kalogerakis, Siddhartha Chaudhuri, Daphne Koller, Vladlen Koltun
ACM Transactions on Graphics, Vol. 31, No. 4 [PAPER] [PAGE] [VIDEO]
(also presented in SIGGRAPH 2012, Los Angeles, USA)

Abstract: We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new generative model of component-based shape structure. The model represents probabilistic relationships between properties of shape components, and relates them to learned underlying causes of structural variability within the domain. These causes are treated as latent variables, leading to a compact representation that can be effectively learned without supervision from a set of compatibly segmented shapes. We evaluate the model on a number of shape datasets with complex structural variability and demonstrate its application to amplification of shape databases and to interactive shape synthesis.

Learning Hatching for Pen-and-Ink Illustration of Surfaces
Evangelos Kalogerakis, Derek Nowrouzezahrai, Simon Breslav, Aaron Hertzmann
ACM Transactions on Graphics, Vol. 31, No. 1 [PAPER][PAGE]
(also presented in SIGGRAPH 2012, Los Angeles, USA)

Abstract: This paper presents an algorithm for learning hatching styles from line drawings. An artist draws a single hatching illustration of a 3D object. Their 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 features to these 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.

Probabilistic Reasoning for Assembly-Based 3D Modeling [PAPER] [PAGE] [VIDEO]
Siddhartha Chaudhuri, Evangelos Kalogerakis, Leonidas Guibas, Vladlen Koltun
ACM Transactions on Graphics, Vol. 30, No. 4
(also presented in SIGGRAPH 2011, Vancouver, Canada)

Abstract: Assembly-based modeling is a promising approach to broadening the accessibility of 3D modeling. In assembly-based modeling, new models are assembled from shape components extracted from a database. A key challenge in assembly-based modeling is the identification of relevant components to be presented to the user. In this paper, we introduce a probabilistic reasoning approach to this problem. Given a repository of shapes, our approach learns a probabilistic graphical model that encodes semantic and geometric relationships among shape components. The probabilistic model is used to present components that are semantically and stylistically compatible with the 3D model that is being assembled. Our experiments indicate that the probabilistic model increases the relevance of presented components.

Learning 3D Mesh Segmentation and Labeling [PAPER] [PAGE]
Evangelos Kalogerakis, Aaron Hertzmann, Karan Singh
ACM Transactions on Graphics, Vol. 29, No. 3, July 2010
(also presented in Siggraph 2010, Los Angeles, USA, July 2010)

Abstract: 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 between labels of neighboring faces. The objective function is learned from a collection of labeled training meshes. The algorithm uses hundreds of geometric and contextual label features and learns different types of segmentations for different tasks, without requiring manual parameter tuning. Our algorithm achieves a significant improvement in results over the state-of-the-art when evaluated on the Princeton Segmentation Benchmark, often producing segmentations and labelings comparable to those produced by humans.

Image Sequence Geolocation with Human Travel Priors [PAPER] [PAGE]
Evangelos Kalogerakis, Olga Vesselova, James Hays, Alexei Efros, Aaron Hertzmann
Proceedings of the IEEE International Conference on Computer Vision 2009, Kyoto, Japan (oral presentation)

Abstract: This paper presents a method for estimating geographic location for sequences of time-stamped photographs. A prior distribution over travel describes the likelihood of traveling from one location to another during a given time interval. This distribution is based on a training database of 6 million photographs from Flickr.com. An image likelihood for each location is defined by matching a test photograph against the training database. Inferring location for images in a test sequence is then performed using the Forward-Backward algorithm, and the model can be adapted to individual users as well. Using temporal constraints allows our method to geolocate images without recognizable landmarks, and images with no geographic cues whatsoever. This method achieves a substantial performance improvement over the best-available baseline, and geolocates some users’ images with near-perfect accuracy.

Data-driven curvature for real-time line drawing of dynamic scenes [PAPER] [PAGE] [VIDEO]
Evangelos Kalogerakis, Derek Nowrouzezahrai, Patricio Simari, James McCrae, Aaron Hertzmann, Karan Singh
ACM Transactions on Graphics, Vol. 28, No. 1, January 2009
(also presented in SIGGRAPH 2009, New Orleans, USA, August 3 - 9, 2009)

Abstract: This paper 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 derivatives. Unfortunately, these curvatures and their derivatives cannot be computed in real-time for animated, deforming objects. In a preprocessing step, our method learns the mapping from a low-dimensional set of animation parameters to surface curvatures for a deforming 3D mesh. The learned model can then accurately and efficiently predict curvatures and their derivatives, enabling real-time object-space rendering of suggestive contours and other such curves. This represents an order-of-magnitude speed-up over the fastest existing algorithm capable of estimating curvatures and their derivatives accurately enough for many different types of line drawings. The learned model can generalize to novel animation sequences, and is also very compact, requiring a few megabytes of storage. We demonstrate our method for various types of animated objects, including skeleton-based characters, cloth simulation and facial animation, using a variety of non-photorealistic rendering styles.

Multi-objective shape segmentation and labeling [PAPER] [VIDEO]
Patricio Simari, Derek Nowrouzezahrai, Evangelos Kalogerakis, Karan Singh
Special Issue of the Computer Graphics Forum, Vol. 28, No. 5, August 2009
(also presented in Eurographics Symposium of Geometry Processing 2009, Berlin, Germany, July 15-17)

Abstract: In this paper, we perform segmentation and labeling of shapes based on a simultaneous optimization of multiple heterogenous objectives that capture application-specific segmentation criteria. We present a number of efficient objective functions that capture useful shape adjectives (compact, flat, narrow, perpendicular, etc.) Segmentation descriptions within our framework combine multiple such objective functions with optional labels to define each part. The optimization problem is simplified by proposing weighted Voronoi partitioning as a compact and continuous parametrization of spatially embedded shape segmentations. This partition is automatically labeled to optimize heterogeneous part objectives and the Voronoi centers and their weights optimized using Generalized Pattern Search. We illustrate our framework using several diverse segmentation applications: bounding volume hierarchies for path tracing, and automatic rig and clothing transfer between animation characters.

Shadowing Dynamic Scenes with Arbitrary BRDFs [PAPER] [VIDEO]
Derek Nowrouzezahrai, Evangelos Kalogerakis, Eugene Fiume
Special Issue of the Computer Graphics Forum, Vol. 28, No. 2, April 2009
(also presented in Eurographics 2009, Berlin, Germany, March 30 - April 3)

Abstract: We present a real-time relighting and shadowing method for dynamic scenes with varying lighting, view and BRDFs. Our approach is based on a compact representation of reflectance data that allows for changing the BRDF at run-time and a data-driven method for accurately synthesizing self-shadows on articulated and deformable geometries. Unlike previous self-shadowing approaches, we do not rely on local blocking heuristics. We do not fit a model to the BRDF-weighted visibility, but rather only to the visibility that changes during animation. In this manner, our model is more compact than previous techniques and requires less computation both during fitting and at run-time. Our reflectance product operators can re-integrate arbitrary low-frequency view-dependent BRDF effects on-the-fly and are compatible with all previous dynamic visibility generation techniques as well as our own data-driven visibility model. We apply our reflectance product operators to three different visibility generation models, and our data-driven model can achieve framerates well over 300Hz.

Extracting lines of curvature from noisy point clouds [PAPER] [PAGE]
Evangelos Kalogerakis, Derek Nowrouzezahrai, Patricio Simari, Karan Singh
Special Issue of the Computer-Aided Design on Point-Based Computational Techniques, Vol. 41, No. 4, April 2009

Abstract: We present a robust framework for extracting lines of curvature from point clouds. First, we show a novel approach to denoising the input point cloud using robust statistical estimates of surface normal and curvature which automatically rejects outliers and corrects points by energy minimization. Then the lines of curvature are constructed on the point cloud with controllable density. Our approach is applicable to surfaces of arbitrary genus, with or without boundaries, and is statistically robust to noise and outliers while preserving sharp surface features. We show our approach to be eective over a range of synthetic and real-world input datasets with varying amounts of noise and outliers. The extraction of curvature information can benefit many applications in CAD, computer vision and graphics for point cloud shape analysis, recognition and segmentation. Here, we show the possibility of using the lines of curvature for feature-preserving mesh construction directly from noisy point clouds.