(peer-reviewed papers, published in international journals and conferences)
AttribIt: Content Creation with Semantic Attributes
Siddhartha Chaudhuri, Evangelos Kalogerakis, Stephen Giguere, Thomas Funkhouser
ACM UIST 2013 (conditionally accepted, under minor revisions)
Abstract: We present Attribit, an approach for people to create visual content using relative semantic attributes expressed in linguistic terms. During an off-line processing step, Attribit learns semantic attributes for design components that reflect the high-level intent people may have for creating content in a domain (e.g., adjectives such as “dangerous,” “scary,” or “strong”) and ranks them according to the strength of each learned attribute. Then, during an interactive design session, a person can explore different combinations of visual components using commands based on relative attributes (e.g., “make this part more dangerous”). Novel designs are assembled in real-time as the strength of selected attributes are varied, enabling rapid, in-situ exploration of candidate designs. Experiments suggest that this design interface is an effective alternative for novices performing tasks with high-level design goals.
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.
|[animation dataset by Joel Anderson ©]
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.
|Eigentransport for Efficient and Accurate All-Frequency Relighting [PAPER] [PAGE]
Derek Nowrouzezahrai, Patricio Simari, Evangelos Kalogerakis, Eugene Fiume
Proceedings of the ACM Graphite 2007, Perth, Australia, Dec 2-4 2007 - Best
Abstract: We present a method for creating a geometry-dependent basis for
precomputed radiance transfer. Unlike previous PRT bases, ours is
derived from principal component analysis of the sampled transport
functions at each vertex. It allows for efficient evaluation of shading,
has low memory requirements and produces accurate results
with few coefficients. We are able to capture all-frequency effects
from both distant and near-field dynamic lighting in real-time and
present a simple rotation scheme. Reconstruction of the final shading
becomes a low-order dot product and is performed on the GPU.
| Robust statistical estimation of curvature on discretized surfaces [PAPER] [PAGE]
Evangelos Kalogerakis, Patricio Simari, Derek Nowrouzezahrai, Karan
Proceedings of the Eurographics Symposium on Geometry
Processing, Barcelona, Spain, July 4-6 2007
Abstract: A robust statistics approach to curvature estimation on discretely sampled surfaces, namely polygon meshes and
point clouds, is presented. The method exhibits accuracy, stability and consistency even for noisy, non-uniformly
sampled surfaces with irregular configurations. Within an M-estimation framework, the algorithm is able to reject
noise and structured outliers by sampling normal variations in an adaptively reweighted neighborhood around
each point. The algorithm can be used to reliably derive higher order differential attributes and even correct noisy
surface normals while preserving the fine features of the normal and curvature field. The approach is compared
with state-of-the-art curvature estimation methods and shown to improve accuracy by up to an order of magnitude
across ground truth test surfaces under varying tessellation densities and types as well as increasing degrees of
noise. Finally, the benefits of a robust statistical estimation of curvature are illustrated by applying it to the popular
applications of mesh segmentation and suggestive contour rendering.
meshes: Hierarchical mesh segmentation based on planar
symmetry [PAPER] [PAGE]
Patricio Simari, Evangelos
Proceedings of the Eurographics Symposium on Geometry
Processing, Cagliari, Italy, June 26-28, 2006
Abstract: Meshes representing real world objects, both artist-created and scanned, contain a high level of redundancy due to approximate planar reflection symmetries, either global or localized to different subregions. An algorithm is presented for detecting such symmetries and segmenting the mesh into the symmetric and remaining regions. The method has foundations in robust statistics and is resilient to structured outliers which are present in the form of the non symmetric regions of the data. Also introduced is an application of the method: the folding tree data structure. The structure encodes the non redundant regions of the original mesh as well as the reflection planes and is created by the recursive application of the detection method. This structure can then be unfolded to recover the original shape. Applications include mesh compression, repair as well as mesh processing acceleration by limiting computation to non redundant regions and propagation of results.
|Coupling ontologies with graphics content for Knowledge Driven Visualization [PAPER] [PAGE]
Evangelos Kalogerakis, Nektarios Moumoutzis, Stavros Christodoulakis
Proceedings of the IEEE Virtual Reality 2006, Virginia, USA, 25-28 March 2006
Abstract: A great challenge in information visualization today is to provide models and software that effectively integrate the graphics content of scenes with domain-specific knowledge so that the users can effectively query, interpret, personalize and manipulate the visualized information. Moreover, it is important that such applications are interoperable in the semantic web environment and thus, require that the models and software supporting them integrate state-of-the-art international standards for knowledge representation, graphics and multimedia. In this paper, we present a model and a software framework for the semantic web for the development of interoperable intelligent visualization applications that support the coupling of graphics and virtual reality scenes with domain knowledge of different domains. We also provide methods for knowledge driven information visualization and visualization-aided decision making based on inference by reasoning.