SEMI-GLOBAL MATCHING (SMG) COST COMPRESSION

摘要

This disclosure describes techniques for performing semi-global matching (SGM) path cost compression. In some examples, the techniques may perform disparity-dependent sub-sampling of a set of SGM path costs where the sub-sampling ratio is determined based on a candidate disparity level. The sub-sampled SGM path costs may be stored in a memory. When retrieved from memory, the sub-sampled SGM path costs may be interpolated to reconstruct the other path costs not stored in the memory. The reconstructed path costs may be used for further SGM processing. In further examples, the techniques may perform disparity-dependent quantization on the SGM path costs or the sub-sampled SGM path costs, and store the quantized SGM path costs in memory. The techniques of this disclosure may reduce bandwidth as well as reduce the memory footprint needed to implement an SGM algorithm.

主权项

1. A method comprising, for each of a plurality of candidate disparity levels:
calculating, with processing circuitry, a plurality of costs for a plurality of pixels in a scan region based on the respective candidate disparity level; calculating, with the processing circuitry, a plurality of semi-global matching (SGM) path costs for a subset of the pixels that form a path in the scan region based on the costs and the respective candidate disparity level; determining, with the processing circuitry, a sub-sampling ratio based on the respective candidate disparity level; sub-sampling, with the processing circuitry, the SGM path costs based on the determined sub-sampling ratio; and storing, with the processing circuitry, the sub-sampled SGM path costs for the respective candidate disparity level in a memory.