csqiangwen / video_waterdrop_removal_in_driving_scenes Goto Github PK
View Code? Open in Web Editor NEW[ICRA2023] Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes
License: MIT License
[ICRA2023] Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes
License: MIT License
Dear author,
I'd like to try your proposed model on my own dataset. But I don't know the difference between dataset rainy_vid and rainy_vid_blur and have no idea how to get the blur images. Could you please give me some advice?
Hope for your quick reply!
Best wishes to you!
作者您好,您在论文中提到模型是用一个train_img和一个train_vid进行联合训练得到,但是我发现在train_img这个训练集上(您之前在issues里给出的下载地址)是没有mask这一项的,但是代码的dataloader是有读取mask这一操作的。不知您能否提供包含mask的train_img训练集?
此外,我注释掉了代码中关于train_img训练集的一些相关代码,即只使用train_vid进行训练。在进行了与论文中同样的迭代次数后,我对test/syn和test/real分别进行了测试,其中对于test/syn的结果是符合论文结果的,但是对于test/real即真实场景的图片下的测试效果很不理想,几乎无法正常消除雨滴。
请问这是因为没有与自然图片train_img联合训练造成的影响吗?又或者是我忽略了哪些细节呢?恳请作者解惑!
作者你好,感谢你分享这个很棒的工作。我对此项目很感兴趣,但是在下载数据集时遇到了一些问题,请问有百度网盘的链接吗,我觉得通过百度网盘来下载数据集可能会更快一些,谢谢!
Dear author,
I just wanted to say thanks for creating and sharing your project on GitHub. It's been really helpful to me.
I did have a question about your project, though. When I downloaded the dataset you provided and tried to train the model. An error occured "FileNotFoundError: [Errno 2] No such file or directory: './dataset/train/train_img/train/data'", it seems like you maybe forget to upload the data in above directory but only the "./dataet/train/train_vid".
If you have a few minutes to spare, I would really appreciate any guidance or direction you could provide on this issue. Thanks again for your awesome work and for taking the time to read this message.
Best wishes.
您的这篇工作十分有趣,给了我很大的启发,想问一下 关于合成雨滴数据集的代码,可以提供一下么,谢谢。
我看到Github上发布的数据集只有train_vid视频训练集,但是代码和论文中都有一个联合训练的图像数据集,但是我并未发现提供的数据集中有train_img这一选项。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.