Question about the confidence map

[luomomo]

Hi, I since in the demo the confidence map is fixed. I change it the another confidence image is in range [0,255]( from LRC and depth - LRC,I test both ),but the out output image is all black ,what happens ? Is there any I need to notice when using confidence map？

[SilentSkyWalker]

hi，you can have a try on [1,255] instead of [0,255]-------- 原始邮件 --------发件人： luomomo <notifications@github.com>日期： 2019年9月11日周三 21:52收件人： poolio/bilateral_solver <bilateral_solver@noreply.github.com>抄送： Subscribed <subscribed@noreply.github.com>主 题： [poolio/bilateral_solver] Question about the confidence map (#4)Hi, I since in the demo the confidence map is fixed. I change it the another confidence image is in range [0,255]( from LRC and depth - LRC,I test both ),but the out output image is all black ,what happens ? Is there any I need to notice when using confidence map？ —You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or mute the thread.

[jonbarron]

The only constraint on the confidence is that it's non-negative. This code uses uint8 images but that's just a side effect of how image formats work. If you're getting all-black input, my guess is that your confidences are very low or zero, or your input is black. Try scaling your confidences up by a global scalar (which is equivalent to just decreasing the smoothness parameter).

[wch1996]

Hello,Did you slove this problem?I meet seem problem too,the output is all black

[luomomo]

O(∩_∩)O非常感谢您给我发来邮件，稍后我会仔细阅读。