Conference 3 Dec - 6 Dec Exhibition 4 Dec - 6 Dec


    Technical Papers

    01 Full Conference1 - Full Conference One Day



    Paintings, Sketches and Buildings

    Thursday, 04 December

    11:00 - 12:45

    Jasmine Hall

    Autocomplete Painting Repetitions

    We present an interactive digital painting system that auto-completes tedious repetitions while preserving nuanced variations and maintaining natural flows.

    Jun Xing, The University Of Hong Kong
    Li-Yi Wei, The University of Hong Kong
    Hsiang-Ting Chen, Hasso-Plattner-Institute

    BiggerPicture: Data-Driven Image Extrapolation Using Graph Matching

    We have suggested a data-driven method for a challenging task---extensively extrapolating an image. Our graph based method can automatically retrieve appropriate library images suitable as a basis for extrapolation with generally correct appearance; the following extrapolation stage ensures boundary consistency in the result.

    Miao Wang, Tsinghua University
    Yu-Kun Lai, Cardiff University
    Yuan Liang, Tsinghua University
    Ralph Martin, Cardiff University
    Shi-Min Hu, Tsinghua University

    Sketch Classification and Classification-Driven Analysis using Fisher Vectors

    We introduce an approach for sketch classification that significantly outperforms existing techniques, achieving a recognition rate which is close to human performance. We then propose a different benchmark for the evaluation of sketch classification algorithms and, finally, we perform classification-driven analysis which recovers semantic aspects of the individual sketches.

    Rosalia Schneider, Katholieke Universiteit Leuven
    Tinne Tuytelaars, Katholieke Universiteit Leuven

    Data-driven Segmentation and Labeling of Freehand Sketches

    This paper presents a data-driven approach to derive part-level segmentation and semantically label individual components of free-hand sketches, which depict single objects consisting of multiple parts

    Zhe Huang, City University of Hong Kong
    Hongbo Fu, City University of Hong Kong
    Rynson Lau, City University of Hong Kong

    ConstructAide: Analyzing and Visualizing Construction Sites through Photographs and Building Models

    We describe a set of tools for analyzing, visualizing, and assessing architectural/construction progress with unordered photo collections and 3D building models. Our system allows a user, to explore the construction site seamlessly in time, monitor the progress of construction, assess errors and deviations, and create photorealistic architectural visualizations.

    Kevin Karsch, University of Illinois at Urbana-Champaign
    Mani Golparvar-Fard, University of Illinois at Urbana-Champaign
    David Forsyth, University of Illinois at Urbana-Champaign

    Back to Top
    Go Back