mahmoudnafifi/C5

Issues

• Question about aug_data.json metadata generation

  #15 opened 14 days ago by DY112
  1

• Testing results

  #14 opened 8 months ago by RafiqueA03
  3

• Hello, I'm very interested in the work of C5, but I have a question regarding data collection. I'd like to know what kind of camera settings were used to capture these color-shifted images. When I take pictures with my EOS 600D, they appear as normal white, but due to lighting conditions, there is some color deviation. Can this also be considered as a color constancy task?

  #12 opened a year ago by lf22222
  2

• Many detaild questions

  #13 opened a year ago by shuwei666
  1

• some question about the input image type

  #11 opened 2 years ago by TLcode001
  2

• Some questions about the Training and Testing details

  #10 opened 2 years ago by Bright-Shawn
  1

• Question about your data augmentation method and CIE XYZ color space

  #9 opened 2 years ago by DY112
  2

• What is the difference between the white balance and the color constancy?

  #8 opened 2 years ago by ToChangeBetter
  1

• If I have an color deviation image that doesn't know the ground truth, can the network correct it?

  #7 opened 2 years ago by ToChangeBetter
  1

• I can't understand (In src/ops.py, the function add_camera_name(dataset_dir) can be used to rename image filenames and corresponding ground-truth JSON files. Each JSON file should include a key named either illuminant_color_raw or gt_ill that has the ground-truth illuminant color of the corresponding image).Can you help me ?

  #6 opened 2 years ago by ToChangeBetter
  1

• Where is the pretrain model ?

  #5 opened 2 years ago by ToChangeBetter
  2

• about preprocessing of the input image

  #3 opened 3 years ago by SHMCU
  1

• what dataset is the pre-trained model trained on?

  #2 opened 3 years ago by SHMCU
  1

• json files

  #1 opened 3 years ago by SHMCU
  1