2011 · 56 citations · 15 references
ComputingComputer ScienceHigh-performance ComputingComputer GraphicsComputer VisionParallel Computing3D ReconstructionDepth EstimationGraphics Processing Unit ArchitectureGraphics Processing Unit ComputingGraphics Processing UnitsStereo VisionDense Depth EstimationDepth Map ReconstructionDisparity EstimationDisparity Map EstimationParallelizationSemi-global MatchingStereo MatchingThroughput
This paper presents the design, implementation and evaluation of new parallelization schemes for performing dense disparity estimation based on non-parametric rank transform and semi-global matching on Graphics Processing Units (GPUs). A detailed analysis of the performance limitating factors (memory throughput, instruction throughput, etc.) for each part of the parallel implementation is performed. Thus, a highly optimized mapping for each parallelization scheme onto the resources of the GPU is obtained. The resulting implementation performs disparity estimation at 27 frames per second for 1024×768 pixel images with 128 disparity levels on a Nvidia Tesla C2050 GPU.
15
High-accuracy stereo depth maps using structured light
Daniel Scharstein, Richard Szeliski · 2003 · 1.5K citations
Evaluation of Cost Functions for Stereo Matching
Heiko Hirschmüller, Daniel Scharstein · 2007 · 1.1K citations