ExposureDiffusion

ExposureDiffusion copied to clipboard

About Training Time

3

I appreciate your research efforts. I have a keen interest in your work. I would like to retrain the model following your paper. Could you provide an estimate of the...

conutqiqi

Hi, Thanks for your great work, when I try to train this,I run python3 train_syn.py --name sid_Pg --include 4 --noise P+g --model eld_iter_model --with_photon --adaptive_res_and_x0 --iter_num 2 --epoch 300 --auxloss...

AAAeray

1. How to check whether the training is converged? I saw the values of Pixel, w1 and w2 on training panel but I don't know the exact meaning of these...

xinyuz8270

i want make image exposure,can it ?

shaoyandea

Custom lowlight data

1

How to test my own lowlight imges

zkaiWu

Thanks for your great works! In 'ExposureDiffusion: Learning to Expose for Low-light Image Enhancement Supplementary Material' 1. Detail of proofs, there might exist a error. ```math \mathbb{E}_{q\left(X_{r e f}\right)}\left[\mathbb{E}_{p_{\Theta}\left(X_{0: T}\right)}\left[\frac{p_{\Theta}\left(X_T\right)}{q\left(X_T...

Henry-Bi

Mask used by forward and output function

1

Is mask used in [forward function](https://github.com/wyf0912/ExposureDiffusion/blob/29b125a0ae2cc0ca5f52395c65f4f4e340a20f97/models/losses.py#L33C14-L33C14) a different one than the soft mask used in output function? (seems different) And is there any insight on the the threshold value? Thanks!

Zhenyi-Liu

您好，代码（https://github.com/wyf0912/ExposureDiffusion/blob/29b125a0ae2cc0ca5f52395c65f4f4e340a20f97/models/ELD_model_iter.py#L190） 中ratio_next-1按照论文应该是ratio_next-ratio_current是吗？这边ratio_current固定为1（lamda_T=1）是因为都想用最初的图像进行计算增量，而非利用上一时刻的预测图像计算增量吗？

czzbb

Hello,thanks for your outstanding work. This is my description for beginners to quick start. 

weiruihhh