UrbanScan: 3D modeling of urban scenes

  • "Datasets for PPR"
  • "How StereoScan Works"
  • "PPR Reconstructions"

Information

For more information about the project contact us.

Computer Vision:

  • carolinasraposo(at)gmail.com
  • jpbar(at)isr.uc.pt
    Google Academic

GPU Computing:

  • cgraca(at)co.it.pt
    Google Academic
  • gff(at)co.it.pt
    Google Academic

Supported by:






Conferences

    1. R. Ralha, G. Falcão, J. Andrade, M. Antunes, J. P. Barreto, U. Nunes, Distributed dense stereo matching for 3D reconstruction using parallel-based processing advantages, IEEE Int. Conference on Acoustics, Speech, and Signal Processing (ICASSP15), May 2015 (pdf)
    2. C. Raposo, M. Antunes, and J. P. Barreto, “Piecewise-Planar StereoScan: Structure and Motion from Plane Primitives,” European Conference in Computer Vision, Zurich, September 2014 (acceptance ratio: 25%) (pdf)
    3. Vasco Mota, G. Falcão, M. Antunes, J. P. Barreto, U. Nunes, Using the GPU for fast symmetry-based dense stereo matching in high resolution images, IEEE Int. Conference on Acoustics, Speech, and Signal Processing (ICASSP14), Florence, Italy, May 2014 (pdf)

Journals

    1. Carlos Graca, Carolina Raposo, João P. Barreto, Urbano Nunes, and Gabriel Falcao, "GPU-accelerated uncapacitated facility location and semi-dense SymStereo pipelines for piecewise-planar-based 3D reconstruction," Journal of Real-Time Image Processing, Springer, Vol. 18, pp. 445–461, 2021. https://doi.org/10.1007/s11554-020-00974-z (pdf)
    2. Michel Antunes and J. P. Barreto, “Piecewise Planar Reconstruction using Two- Views,” Image and Vision Computing, Image and Vision Computing, vol. 46, pp. 47-63, 2016. (pdf)
    3. J. Maria, J. Amaro, G. Falcao, and L. A. Alexandre. "Stacked Autoencoders using Low-power Accelerated Architectures for Object Recognition in Autonomous Systems", Neural Processing Letters, Springer, DOI: 10.1007/s11063-015-9430-9, April 2016. (pdf)
    4. R. Ralha, G. Falcao, J. Amaro, V. Mota, M. Antunes, J. Barreto, and U. Nunes. "Parallel Refinement of Slanted 3D Reconstruction using Dense Stereo Induced from Symmetry", Journal of Real-Time Image Processing, Springer, DOI: 10.1007/s11554-016-0592-0, May 2016. (pdf)
    5. Michel Antunes and J. P. Barreto, “SymStereo: Stereo Matching using Induced Symmetry”, International Journal of Computer Vision, pp. 1–21, Sep. 2014 (pdf)

MSc Thesis

    1. R. Ralha, Real-time symmetry-based dense stereo matching for 3D reconstruction, MSc dissertation (supervisors: G. Falcão and J.Barreto), FCTUC, February 2015
    2. V. Mota, Using Fast Fusion Moves to Solve the Uncapacitated Facility Location (UFL) Problem: Applications in Computer Vision, MSc dissertation (supervisors: J.Barreto and G. Falcão), FCTUC, February 2015

Technical Reports

    1. Carlos Graça, “Fast Parallel SymStereo and UFL (message passing  - max-sum) algorithms applied to Piecewise Planar 3D reconstruction using hybrid CPU + GPU and multi-GPU architectures”, Technical Report, December 2015 (pdf)
    2. João Marcos, “SymStereo Acceleration, Smart Lines Detection and Stereo Datasets Acquisition of Distinct Challenging Urban Scenarios”, Technical Report, 2014

Invited Talks

    1. G. Falcão, “GPUs and parallel computing towards 3D reconstruction” under the participation at the international workshop on “Interactive 3D models from photos”, from the Architectural Democracy Group (http://www.aibeo.com/#!architectural-democracy-research/c1m2d) at the University of Aalto, in Helsinki, Finland, September 2015