You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I try to run this project with my raw images, the output image is blur and has some artifacts; Is the problem of params alpha/beta?
How can i match them with this project? How to calibrate the alpha/beta params?
Looking forward to your reply.
The text was updated successfully, but these errors were encountered:
Artefacts can have many different causes, and I guess you are mentionning the bright colors next sharp edges. It seems to be inherent to the method, and is boosted by the post-processing. We found that applying this method could remove them efficiently.
For the blury part, you could use a stronger unsharp mask as post precessing. Blurry spots can also indicate that too many frames where rejected, which could be either due to a bad frame alignment or a wrong decision of the robustness module. If it comes from the rejection (which you can check by running the algorithm without the robustness mask), you can try to get alpha and beta using noise profiling methods like this.
My guess is that some tricky spots can get blured because the implementation is not perfect, the alignment module and the robustness mask can probably be tweaked to have better results.
Hi Jamy:
I try to run this project with my raw images, the output image is blur and has some artifacts; Is the problem of params alpha/beta?
How can i match them with this project? How to calibrate the alpha/beta params?
Looking forward to your reply.
The text was updated successfully, but these errors were encountered: