Research projects associated with Ph.D.

Non-uniform Hierarchical Geo-consistency for Multi-baseline Stereo

non-uniform
  • Abstract:

    We propose a new and flexible hierarchical multi-baseline stereo algorithm that features a non-uniform spatial decomposition of the disparity map. The visibility computation and refinement of the disparity map are integrated into a single iterative framework that does not add extra constraints to the cost function. This makes it possible to use a standard efficient stereo matcher during each iteration. The level of refinement is increased automatically where it is needed in order to preserve a good localization of boundaries. While two graph-theoretic stereo matchers are used in our experiments, our framework is general enough to be applied to many others. The validity of our framework is demonstrated using real imagery with ground truth.

  • Marc-Antoine Drouin, Martin Trudeau and Sébastien Roy, Non-Uniform Hierarchical Geo-consistency for Multi-baseline Stereo, CRV, Montreal, Canada, May 2007.
  • article (pdf)
  • slides

Improving Border Localization of Multi-Baseline Stereo Using Border-Cut

border
  • Abstract:

    This paper presents a novel algorithm that improves the localization of disparity discontinuities of disparity maps obtained by multi-baseline stereo. Rather than associating a disparity label to every pixel of a disparity map, it associates a position to every disparity discontinuity. This formulation allows us to find an approximate solution to a 2D labeling problem with robust smoothing term by minimizing multiple 1D problems, thus making possible the use of dynamic programming. Dynamic programming allows the efficient computation of the visibility of most of the cameras during the minimization. Whilst the proposed minimization strategy is particularly suitable for stereo with occlusion, it may be used with other labeling problems.

  • Marc-Antoine Drouin, Martin Trudeau and Sébastien Roy, Improving Border Localization of Multi-Baseline Stereo Using Border-Cut, CVPR, New York, USA, June 2006.
  • article (pdf)
  • slides (pdf)
  • Marc-Antoine Drouin, Martin Trudeau and Sébastien Roy, Improving Border Localization of Multi-Baseline Stereo Using Border-Cut, IJCV, Volume 83, Issue 299.
  • article (link)

Geo-consistency for Wide Multi-Camera Stereo

Pyramid
  • Abstract:

    This paper presents a new model to overcome the occlusion problems coming from wide baseline multiple camera stereo. Rather than explicitly modeling occlusions in the matching cost function, it detects occlusions in the depth map obtained from regular efficient stereo matching algorithms. Occlusions are detected as inconsistencies of the depth map by computing the visibility of the map as it is reprojected into each camera. Our approach has the particularity of not discriminating between occluders and occludees. The matching cost function is modified according to the detected occlusions by removing the offending cameras from the computation of the matching cost. The algorithm gradually modifies the matching cost function according to the history of inconsistencies in the depth map, until convergence. While two graph-theoretic stereo algorithms are used in our experiments, our framework is general enough to be applied to many others. The validity of our framework is demonstrated using real imagery with different baselines.

  • Marc-Antoine Drouin, Martin Trudeau and Sébastien Roy, Geo-consistency for Wide Multi-Camera Stereo, CVPR, San Diego, USA, June 2005.
  • article (pdf) (ps)
  • Technical Report (pdf)
  • poster (pdf)

Fast Multiple-baseline Stereo with Occlusion

Pyramid
  • Abstract:

    This paper presents a new and fast algorithm for multi-baseline stereo designed to handle the occlusion problem. The algorithm is a hybrid between fast heuristic occlusion overcoming algorithms that precompute an approximate visibility and slower methods that use correct visibility handling. Our approach is based on iterative dynamic programming and computes simultaneously the disparity and the camera visibility. Interestingly, dynamic programming makes it possible to compute exactly part of the visibility information. The remainder is obtained through heuristics. The validity of our scheme is established using real imagery with ground truth and compares favorably with other state-of-the-art multi-baseline stereo algorithms.

  • Marc-Antoine Drouin, Martin Trudeau and Sébastien Roy, Fast Multiple-baseline Stereo with Occlusion, 3DIM, Ottawa, Canada, June 2005.
  • article (pdf) (ps)
  • Technical Report (pdf)
  • slides (pdf)
  • Code (tar.gz)

Non-Uniform Hierarchical Pyramid Stereo for Large Images

Pyramid
  • Abstract:

    This paper addresses the stereo correspondence problem where the images are large enough to make stereo matching difficult. In order to reduce the problem size, we propose a new non-uniform hierarchical scheme with the ability to handle different coarseness levels simultaneously. Our framework, based on a maximum flow formulation, allows a much better localization of object boundaries where large depth discontinuities are present. The uniform decomposition fails to localize precisely such borders because it makes the assumption that surfaces are smooth in order to correct the errors from one coarseness level to the next. Our disparity estimation accurately localizes large depth discontinuities and then focus on increasing the resolution of smooth surfaces. Results on synthetic and real images demonstrate the validity of our framework.

  • Sébastien Roy and Marc-Antoine Drouin, Non-Uniform Hierarchical Pyramid Stereo for Large Images, VISION, MODELING , AND VISUALIZATION (VMV'2002), Erlangen, Germany, November 2002, pp 403-410.
  • article (pdf) (ps)
  • slides(pdf)