jinyeying / nighttime_dehaze

[ACMMM2023] "Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution", https://arxiv.org/abs/2308.01738

Hi 👋 I'm Jin Yeying

I am a Senior Researcher at Tencent. I am pursuing my Ph.D. degree at the National University of Singapore (NUS), supervised by Prof. Robby T. Tan. I had my research internship in Adobe, mentored by Prof. Connelly Barnes.

Previously, I completed my M.Sc. degree from the National University of Singapore (NUS); and received my B.Eng degree from University of Electronic Science and Technology of China (UESTC).

My primary research interests include computer vision and deep learning, mainly focusing on image/video generation and enhancement.

Languages and Tools:

nighttime_dehaze's Issues

can you share me the training codes?

Hi @jinyeying , I read your paper, I want to go deep and learn the training codes?

light Source matting

Hello, the light source mask in your article uses alpha matting. Do you manually add scribbles to each light source mask?

about the training way

Hello, may I know if your network was trained using an unpaired or paired approach? In your paper, you mentioned that your network was trained based on a CycleGAN-based network (an unpaired training method). However, in the experimental section, you stated that a paired GTA5 dataset was used for training.

about the compared code "Nighttime defogging using high-low frequency decomposition and grayscale-color networks"

thanks for your work, would like to ask how to get your comparison method "Nighttime defogging using high-low frequency decomposition and grayscale-color networks" testing code

Training Code

Hello! Thank you for your work!⭐⭐⭐

Very Good!👍👍👍

I want to learn this network and retrain in other directions.
Is the training code convenient for public access?

Thank you very much!🌸🌸🌸
Looking forward for your reply！💖💖💖

Test Result

The visual effect deviation obtained from the test weight you provided is significant. Is the weight file you provided the final weight file used in your paper?

Could you please tell me what the parameters and calculations of the network are?