Karan Singh

University of Toronto, Toronto, Ontario, Canada

Are you Karan Singh?

Claim your profile

Publications (58)9.34 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Various algorithms have been proposed to create planar abstractions of 3D models, but there has been no systematic effort to evaluate the effectiveness of such abstractions in terms of perception of the abstracted surfaces. In this work, we perform a large crowd-sourced study involving approximately 70k samples to evaluate how well users can orient gauges on planar abstractions of commonly occurring models. We test four styles of planar abstractions against ground truth surface representations, and analyze the data to discover a wide variety of correlations between task error and measurements relating to surface-specific properties such as curvature, local thickness and medial axis distance, and abstraction-specific properties. We use these discovered correlations to create linear models to predict error in surface understanding at a given point, for both surface representations and planar abstractions. Our predictive models reveal the geometric causes most responsible for error, and we demonstrate their potential use to build upon existing planar abstraction techniques in order to improve perception of the abstracted surface.
    ACM Transactions on Applied Perception (TAP). 08/2013; 10(3).
  • [Show abstract] [Hide abstract]
    ABSTRACT: We explore the design space for using object motion trajectories to create and edit visual elements in various media across space and time. We introduce a suite of pen-based techniques that facilitate fluid stylization, annotation and editing of space-time content such as video, slide presentations and 2D animation, utilizing pressure and multi-touch input. We implemented and evaluated these techniques in DirectPaint, a system for creating free-hand painting and annotation over video.
    Proceedings of the SIGCHI Conference on Human Factors in Computing Systems; 04/2013
  • Noah Lockwood, Karan Singh
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a system for generating full-body animations from the performance on a touch-sensitive tabletop of "finger walking", where two fingers are used to pantomime leg movements. A user study was conducted to explore how users can communicate full-body motion using their hands, which concluded that finger walking is a naturally-chosen and comfortable performance method. Based on contact data recorded during this study, the properties of a variety of performed locomotion types were analyzed to determine which motion parameters are most reliable and expressive for the purpose of generating corresponding full-body animations. Based on this analysis, a compact set of motion features was developed for classifying the locomotion type of a finger performance. A prototype interactive animation system was implemented to generate full-body animations of a known locomotion type from finger walking by estimating the motion path of a finger performance, and editing the path of a corresponding animation to match. The classification accuracy and output animation quality of this system was evaluated in a second user study, demonstrating that satisfying full-body animations can be reliably generated from finger performances.
    Proceedings of the 11th ACM SIGGRAPH / Eurographics conference on Computer Animation; 07/2012
  • Source
    James McCrae, Karan Singh
    [Show abstract] [Hide abstract]
    ABSTRACT: We apply traditional bimanual curve modeling using French curves to the problem of automatic neatening of sketched strokes. Given a sketched input stroke and a set of template French curves we present an approach that fits the stroke using an optimal number of French curve segments. Our algorithm operates in both curvature and point space, reconstructing the salient curvature profiles of French curve segments, while limiting error accumulation resulting from curvature integration. User-controlled parameters allow the neatened stroke to model G2 continuous curves, capture G1 discontinuities, define closed curves and explore the trade-off between fitting error and the number of French curve segments used. We present an interactive sketch stroke neatening implementation to demonstrate the real-time performance of our algorithm and evaluate the quality of its results.
    Sketch Based Interfaces and Modeling, Vancouver, BC, Canada, 5-7 August 2011. Proceedings; 01/2011
  • Source
    Noah Lockwood, Karan Singh
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a system for interactive kinematic editing of motion paths and timing that employs various biomechanical observations to augment and restrict the edited motion. Realistic path manipulations are enforced by restricting user interaction to handles identified along a motion path using motion extrema. An as-rigid-as-possible deformation technique modified specifically for use on motion paths is used to deform the path to satisfy the usermanipulated handle positions. After all motion poses have been adjusted to satisfy the new path, an automatic timewarping step modifies the timing of the new motion to preserve the timing qualities of the original motion. This timewarp is based on biomechanical heuristics relating velocity to stride length and path curvature, as well as the preservation of acceleration for ballistic motion. We show that our system can be used to quickly and easily modify a variety of locomotive motions, and can accurately reproduce recorded motions that were not used during the editing process.
    Proceedings of the 2011 Eurographics/ACM SIGGRAPH Symposium on Computer Animation, SCA 2011, Vancouver, BC, Canada, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Abstract We propose a method for interactive cloning of 3D surface geometry using a paintbrush interface, similar to the continuous cloning brush popular in image editing. Existing interactive mesh composition tools focus on atomic copy-and-paste of preselected feature areas, and are either limited to copying surface displacements, or require the solution of variational optimization problems, which is too expensive for an interactive brush interface. In contrast, our GeoBrush method supports real-time continuous copying of arbitrary high-resolution surface features between irregular meshes, including topological handles. We achieve this by first establishing a correspondence between the source and target geometries using a novel generalized discrete exponential map parameterization. Next we roughly align the source geometry with the target shape using Green Coordinates with automatically-constructed cages. Finally, we compute an offset membrane to smoothly blend the pasted patch with C continuity before stitching it into the target. The offset membrane is a solution of a bi-harmonic PDE, which is computed on the GPU in real time by exploiting the regular parametric domain. We demonstrate the effectiveness of GeoBrush with various editing scenarios, including detail enrichment and completion of scanned surfaces.
    Computer Graphics Forum 01/2011; 30:613-622. · 1.64 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Minimalist object representations or shape-proxies that spark and inspire human perception of shape remain an incompletely understood, yet powerful aspect of visual communication. We explore the use of planar sections, i.e., the contours of intersection of planes with a 3D object, for creating shape abstractions, motivated by their popularity in art and engineering. We first perform a user study to show that humans do define consistent and similar planar section proxies for common objects. Interestingly, we observe a strong correlation between user-defined planes and geometric features of objects. Further we show that the problem of finding the minimum set of planes that capture a set of 3D geometric shape features is both NP-hard and not always the proxy a user would pick. Guided by the principles inferred from our user study, we present an algorithm that progressively selects planes to maximize feature coverage, which in turn influence the selection of subsequent planes. The algorithmic framework easily incorporates various shape features, while their relative importance values are computed and validated from the user study data. We use our algorithm to compute planar slices for various objects, validate their utility towards object abstraction using a second user study, and conclude showing the potential applications of the extracted planar slice shape proxies.
    ACM Trans. Graph. 01/2011; 30:168.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Elasticurves present a novel approach to neaten sketches in real-time, resulting in curves that combine smoothness with user-intended detail. Inspired by natural variations in stroke speed when drawing quickly or with precision, we exploit stroke dynamics to distinguish intentional fine detail from stroke noise. Combining inertia and stroke dynamics, elasticurves can be imagined as the trace of a pen attached to the user by an oscillation-free elastic band. Sketched quickly, the elasticurve spatially lags behind the stroke, smoothing over stroke detail, but catches up and matches the input stroke at slower speeds. Connectors, such as lines or circular-arcs link the evolving elasticurve to the next input point, growing the curve by a responsiveness fraction along the connector. Responsiveness is calibrated, to reflect drawing skill or device noise. Elasticurves are theoretically sound and robust to variations in stroke sampling. Practically, they neaten digital strokes in real-time while retaining the modeless and visceral feel of pen on paper.
    Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, Santa Barbara, CA, USA, October 16-19, 2011; 01/2011
  • Source
    Ryan Schmidt, Karan Singh
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years a wide variety of mesh editing techniques have been developed for tasks such as smoothing, deformation, and parameterization. Comparatively fewer alternatives are available for composition tasks, such as combining parts of existing meshes. As designs often evolve from a combination of existing ideas and models, rapid composition techniques could significantly improve the workflow of mesh-based modeling tools. In our work we are exploring shape reuse and composition problems in 3D mesh modeling.
    International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2010, Los Angeles, California, USA, July 26-30, 2010, Talks Proceedings; 01/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Recently, research in 3D computer graphics and interaction has started to move beyond the narrow domain of single object authoring and inspection, and has begun to consider complex multiscale objects and environments. This generalization of problem scope calls for more general solutions, which are more akin to information visualization techniques than traditional computer graphics approaches. We consider the general problem of the user's understanding of their position and orientation within a multiscale 3D scene and propose a classification of the design space. To ground this theoretical discussion, we present initial explorations into grouping techniques, visualizations, and interactions to facilitate multiscale 3D orientation.
    Proceedings of the International Conference on Advanced Visual Interfaces, AVI 2010, Roma, Italy, May 26-28, 2010; 01/2010
  • Source
    [Show abstract] [Hide abstract]
    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.
    ACM Trans. Graph. 01/2010; 29.
  • [Show abstract] [Hide abstract]
    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 effective 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.
    Computer-Aided Design. 01/2009; 41:282-292.
  • Source
    Conference Paper: Sketch-based path design.
    James McCrae, Karan Singh
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract Sketch-Based Path Design James Palmer McCrae Master of Science Graduate Department of Computer Science University of Toronto 2008 We first present a novel approach to sketching 2D curves with minimally varying cur-
    Proceedings of the Graphics Interface 2009 Conference, May 25-27, 2009, Kelowna, British Columbia, Canada; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present CubeCam, an image-space camera manipulation widget that uses a projected cube to both visualize the relationship of the camera to the scene and as an interaction tool to change that camera. The cube geometry reflects the use of perspective lines by artists in order to establish the scene projection. We allow the user to interactively change the camera by changing the cube's projection in the image plane. We incorporate pie menus, ghosting, and a crossing-style interface to reduce mouse movement and make it simpler for novice users to learn and experiment with the interface. Finally, we provide a novel method for visualizing camera bookmarks.
    Computational Aesthetics 2009: Eurographics Workshop on Computational Aesthetics, Victoria, British Columbia, Canada, 2009; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present EverybodyLovesSketch, a gesture-based 3D curve sketching system for rapid ideation and visualization of 3D forms, aimed at a broad audience. We first analyze traditional perspective drawing in professional practice. We then design a system built upon the paradigm of ILoveS- ketch, a 3D curve drawing system for design professionals. The new system incorporates many interaction aspects of perspective drawing with judicious automation to enable novices with no perspective training to proficiently create 3D curve sketches. EverybodyLovesSketch supports a number of novel interactions: tick-based sketch plane se- lection, single view definition of arbitrary extrusion vectors, multiple extruded surface sketching, copy-and-project of 3D curves, freeform surface sketching, and an interactive perspective grid. Finally, we present a study involving 49 high school students (with no formal artistic training) who each learned and used the system over 11 days, which pro- vides detailed insights into the popularity, power and us- ability of the various techniques, and shows our system to be easily learnt and effectively used, with broad appeal.
    Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology, Victoria, BC, Canada, October 4-7, 2009; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We describe a novel approach to inferring 3D curves from perspective drawings in an interactive design tool. Our methods are based on a traditional design drawing style known as analytic drawing, which supports precise image-space construction of a linear 3D scaffold. This scaffold in turn acts as a set of visual constraints for sketching 3D curves. We implement analytic drawing techniques in a pure-inference sketching interface which supports both single-and multi-view incremental construction of complex scaffolds and curve networks. A new representation of 3D drawings is proposed, and useful interactive drawing aids are described. Novel techniques are presented for deriving constraints from single-view sketches drawn relative to the current 3D scaffold, and then inferring 3D line and curve geometry which satisfies these constraints. The resulting analytic drawing tool allows 3D drawings to be constructed using exactly the same strokes as one would make on paper.
    ACM Trans. Graph. 01/2009; 28.
  • Source
    [Show abstract] [Hide abstract]
    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 (e.g., joint angles) 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, typically requiring a few megabytes of storage at run-time. We demonstrate our method for various types of animated objects, including skeleton-based characters, cloth simulation and blend-shape facial animation, using a variety of non-photorealistic rendering styles.
    ACM Trans. Graph. 01/2009; 28.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A study is described which examines the drawing accuracy of experts when drawing foreshortened projections of 3D curves in ecologically-valid conditions. The main result of this study is that the distribution of error in expert drawings exhibits a bias similar to that previously observed in non-expert subjects, which is dependent on the degree of foreshortening of the imagined drawing surface. A review of existing perceptual studies also finds that only absolute 2D image-space error has been considered, which has been found to be largest with viewing angles of 25--55°. Our visualizations of 3D error indicate that 3D bias continues to increase with decreasing viewing angle. Based on these findings, we analyze current 3D curve drawing techniques for susceptibility to foreshortening bias, and make some suggestions for future sketch-based modeling systems.
    Sketch Based Interfaces and Modeling, New Orleans, Louisiana, USA, 2009. Proceedings; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract We present an interface for 3D object manipulation in which standard transformation tools are replaced with transient 3D widgets invoked by sketching context-dependent strokes. The widgets are automatically aligned to axes and planes determined by the user's stroke. Sketched pivot-points further expand the interaction vocabulary. Using gestural commands, these basic elements can be assembled into dynamic, user-constructed 3D transformation systems. We supplement precise widget interaction with techniques for coarse object positioning and snapping. Our approach, which is implemented within a broader sketch-based modeling system, also integrates an underlying “widget history” to enable the fluid transfer of widgets between objects. An evaluation indicates that users familiar with 3D manipulation concepts can be taught how to efficiently use our system in under an hour.
    Computer Graphics Forum 01/2008; 27:301-310. · 1.64 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce staggered poses---a representation of character motion that explicitly encodes coordinated timing among movement features in different parts of a character's body. This representation allows us to provide sparse, pose--based controls for editing motion that preserve existing movement detail, and we describe how to edit coordinated timing among extrema in these controls for stylistic editing. The staggered pose representation supports the editing of new motion by generalizing keyframe--based workflows to retain high--level control after local timing and transition splines have been created. For densely--sampled motion such as motion capture data, we present an algorithm that creates a staggered pose representation by locating coordinated movement features and modeling motion detail using splines and displacement maps. These techniques, taken together, enable feature--based keyframe editing of dense motion data.
    Proceedings of the 2008 Eurographics/ACM SIGGRAPH Symposium on Computer Animation, SCA 2008, Dublin, Ireland, 2008; 01/2008