fabiotosi92 / unsupervised-confidence-measures Goto Github PK

some are cost(like zsad),
some are similarity(like samm)
the output of zsad confidence map, small value means the right disparity
the outout of samm confidence map, big value means the right disparity.
if their meaning are different,how to put them together?

Hello

While running the code, I encountered a core dump error.

I suspect that the generate_training_samples function in the generate_samples.cpp file is the cause of this issue.

Could you please advise me on how to modify the code to resolve the problem?

Hi,

I come from your paper "Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation". I want to generate some sparse disparity labels but some errors occur when I compile the source files. I am really confused since I seldom use C or C++. Here is the error, could you please help me to solve the problem?

CMakeFiles/bmcv2017.dir/build.make:117: recipe for target 'CMakeFiles/bmcv2017.dir/src/confidence_measures.cpp.o' failed
make[2]: *** [CMakeFiles/bmcv2017.dir/src/confidence_measures.cpp.o] Error 1
CMakeFiles/Makefile2:82: recipe for target 'CMakeFiles/bmcv2017.dir/all' failed
make[1]: *** [CMakeFiles/bmcv2017.dir/all] Error 2
Makefile:90: recipe for target 'all' failed
make: *** [all] Error 2