search

elliottwu / DeepHDR

This is the implementation for Deep High Dynamic Range Imaging with Large Foreground Motions (ECCV'18)
MIT License
186 stars 38 forks source link

How did you generate the ground-truth for your test image #10

Closed hujinhan12 closed 4 years ago

hujinhan12 commented 4 years ago

Hi, I just have one question. When I am trying to test the network with some random captures, I don't know how to create the correct ground-truth for 3 static images I captured. I simply used the triangle method in Kalatari's work, but my output is probably different from yours. If I just read ref_hdr_aligned.hdr and convert it to png using gamma = 2.2, the output image looks very dark. Can you share with me how you created the ground-truth for the test data you captured? Thanks a lot.

elliottwu commented 4 years ago

We directly used the HDR images provided in Kalantari's dataset, and didn't create our own by actually fusing the static shots. Inverse gamma function is only an approximation for tonemapping. The output can appear dull (dim and bleached). To check if you have obtained a "correct" HDR, you may use more powerful tonemapping functions, such as the ones provided in Photomatix.

elliottwu commented 4 years ago

Duplicate of #5