/Stereo-Matching

Stereo Matching on rectified image pair using octree-like representation

Primary LanguagePython

Stereo Matching using Spatial Search Trees

Partially complete implementation of stereo matching for rectified image pairs using octree-like representations.

Tasks (to complete sometime in the future):

  • tree representation
  • naive matching using similarity
  • support for image/videos
  • homogeneity of regions
  • piece-wise continuity
  • vertical smoothness of disparity
  • multi-objective optimization function (genetic algorithms)
  • tree encoding for space optimization
  • utilizing tree as local context for misc tasks

Good References:

  1. Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface Techniques, C Sun, IJCV, 2002. pdf
  2. Multi-Resolution Rectangular Subregioning Stereo Matching Using Fast Correlation and Dynamic Programming Techniques, C Sun, 1998. pdf
  3. Fast Stereo Matching by Iterated Dynamic Programming and Quadtree Subregioning, C Leung, BMVC, 2004. pdf
  4. Stereo Matching Using Global and Local Segmentation, Kim et al. pdf
  5. Multi-resolution stereo matching using genetic algorithm, Gong et al, SMBV 2001. pdf
  6. Genetic-Based Stereo Algorithm and Disparity Map Evaluation, Gong et al, IJCV 2002. pdf
  7. Quadtree-based genetic algorithm and its applications to computer vision, Gong et al, 2004. pdf
  8. Octree Representations of Moving Objects, Ahuja et al, 1984. pdf
  9. Low-level Multiscale Image Segmentation and A Benchmark For Its Evaluation, Akbas et al, 2020. pdf