LED
LED copied to clipboard
Srameo
[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising && [Arxiv 2023] Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
你好，我看代码中处理前会进行归一化，im = (im - bl) / (wl - bl)。我有个问题，就是因为噪声会导致信号上下波动，raw数据我没有做clip，当信号低于bl,或者高于wl会对训练有什么影响。
用您的噪声标定代码标定自己相机的噪声后，生成了一些参数k,row,tl,gauss四个参数， 1，可是在noise_generator中需要用lambda参数这个是从哪里获得的？ 2，noise_generator中有两种合成方式一个是需要标定的一个是虚拟的，我有自己的相机用就是用需要标定的对吧？ 3，在标定噪声对函数中的scale，和ratio 是以怎样的数据类型输入的？scale不是一个固定值么？ 期待您的回复
想问一下大家有无这样的情况 在作者给的LED+NAFNet 和 LED+Restormer 的预训练权重上进行微调 得到的结果 没有在原来的UNet上进行微调的效果好。想寻求一下大家的帮助～ network_g 用的是‘LED-main/options/base/network_g‘下的相应配置文件
The old code in `rawpy/_rawpy.pyx` ``` ndarr.base = self ``` through error `Assignment to a read-only property` should be changed to [issue](https://github.com/letmaik/rawpy/issues/171) ``` np.PyArray_SetBaseObject(ndarr, self) ``` please checkout the official...
您好，我在您提供的的NAFnet预训练网络权重下，进行微调。但是部署的时候图片出现明显的红色噪点，请问您在进行NAFNet部分实验是如何操作的，还是我需要调整finetune部分的细节
Hi, thanks for your VERY impressive work! I have a problem when I installed customized rawpy of ELD. As said in ELD _" type pip install -e . in the...
My image isn't from a specific camera; it's a noisy image from the internet
python scripts/image_process.py -p 'pretrained/LED_Pretrain_None_None_CVPR20_Setting_Ratio100-300.pth' --data_path '/media/ehooph/data/Dataset/speednoise/raw' --save_path '/media/ehooph/data/Dataset/speednoise/change' -opt 'options/LED/pretrain/CVPR20_ELD_Setting.yaml' --led 我使用这行命令运行时报错 Building network... Traceback (most recent call last): File "scripts/image_process.py", line 115, in image_process() File "/home/ehooph/anaconda3/envs/LED-ICCV23/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in...
I am trying to use LED for my mobile phone camera. Could you please clarify some questions about the documentation: https://github.com/Srameo/LED/blob/main/docs/demo.md 1) How to choose best Pretrain checkpoint for the...
