Results for SGM_RVC
Submission data
| Full name | Semi-Global Matching (GPU) (RVC 2020 baseline submission) |
| Description | Reimplementation of SGM on the GPU. Census was used as matching cost. Additionally to disparity, a confidence and error is computed for each pixel. This is included in the runtime.
This is the implementation used on-board the Roboception rc_visard stereo sensors. |
| Parameters | p1=18
p2=32 segmentation filter=80 pixels median filter=5x5 |
| Publication title | Stereo processing by semiglobal matching and mutual information |
| Publication authors | Heiko Hirschmueller |
| Publication venue | TPAMI 2008, Volume 30(2), pp. 328-341 |
| Publication URL | http://ieeexplore.ieee.org/abstract/document/4359315/ |
| Programming language(s) | C++ with CUDA |
| Hardware | GeForce GTX 980 |
| Website | http://www.roboception.com |
| Submission creation date | 10 Mar, 2018 |
| Last edited | 10 Mar, 2018 |
High-res multi-view results
| Info | all | high-res multi-view | indoor | outdoor | courty. | delive. | electro | facade | kicker | meadow | office | pipes | playgr. | relief | relief. | terrace | terrai. |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||||||||||
Low-res many-view results
| Info | all | low-res many-view | indoor | outdoor | lakeside | sand box | storage room | storage room 2 | tunnel |
|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||