ybsong00/drht

Image Correction via Deep Reciprocating HDR Transformation

drht's Issues

About the version of libraries that paper code used

Hi developer, thank you first that shared the code of paper Image Correction via Deep Reciprocating HDR Transformation . Now I want to run your code on my own computer, but your introduce page didn't tell the detail of the version of the libraries that code used, especially the version tensorflow and opencv.

If this request don't bother you, could you tell me the detail of the running environment?

I need the ldr2hdr model to do comparative test

where can i get it

Issues with Pre-Trained model parameters

We used ldr2hdr.npz parameters from the drive link of the pre-trained model. The problem we are facing is that the image we use as input comes out as the output without any changes. The model does not seem to be doing any computation on the image at all.

Also, in the folder structure you have specified, "input --- input ldr images" and "samples --- ldr results", I see the opposite. The LDR jpg images (sky is blown out) are in the samples folder whereas the HDR jpg images (clouds visible) is in the input folder. Am I wrong?

I would like to know more about the training images you used to build your pre-trained model. If I can have that dataset, that will be highly appreciated. I am working on a similar project and I am using this paper as a baseline. My project is limited till the work done in "HDR image reconstruction from a single exposure using deep CNNs"

About the ground truth LDR images of city scene panorama dataset

Hi, I carefully read the paper and found you generate the ground truth LDR images of city scene panorama dataset as follow:

we use the black-box Adobe Photoshop software to empirically generate ground truth LDR images with human supervision.

So I was wondering is that process done automatically, otherwise whether you will release the corresponding data?

Thank you~

About the problem when running ldr2hdr_test.py

Hello, I have downloaded hdrcnn model and put it in ~/DRHT/checkpoint/. After that, I tried to run ldr2hdr_test.py, however, error occurred and said, "TypeError: init() got an unexpected keyword argument 'layer'". I don't know how to solve this problem.
The environment was ubuntu16.04+python3.5+tensorflow-gpu1.10.0.