shiaoming / alike Goto Github PK
View Code? Open in Web Editor NEWALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
Home Page: https://arxiv.org/pdf/2112.02906.pdf
License: BSD 3-Clause "New" or "Revised" License
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
Home Page: https://arxiv.org/pdf/2112.02906.pdf
License: BSD 3-Clause "New" or "Revised" License
Is the model trained with reprojection error works better in Hpatches dataset?such as localization error Anyone tried?
please!!!
请问训练代码中的MegaDepth数据集的json文件能单独发一下吗?
After studying enough, I found that your method is very interesting。Can you provide the training code?
Hi
Do you mind sharing the training code too?
In your paper III-C1:
For a warped keypoint p_AB, we find its closest detected keypoint p_B within th_gt pixels distance as its corresponding keypoint.
I really appreciate your wonderful work and inference code.
While reading your paper, I had a some questions about details.
Is the visual localization of aachen dataset results on the paper only for night, right?
and in case of the unlimited keypoints, which number did you set for the maximum keypoints number?
8000 or more than 8000 ?
Thank you.
Hello, author! The model saved by your training code is in ckpt format, and the test code is in pth format. May I ask how this ckpt is converted to pth?
In order to describe accurately, I want to express it in Chinese.
我对此了解不是十分深刻,但对您文章中提出的训练模式与导数反向传播方式存在一定疑问。文章中使用了NMS层导致整体网络框架不可导,您利用了点邻域的score map构建可导的模式,相当于将一整张图片分割出许多小patch,仅对这些patch做了优化。可是一开始确定NMS点位置的操作是不是没有经过训练优化。您是怎么保证一开始的nms点位置是正确的呢
In your paper you write, that ALIKE achieves higher matching accuracy when trained without the dispersity peak loss. Can you share the trained model(s)?
Thank you for great job!!!
i have a small question about repeatable loss.In ALIKE paper, the matching probability map is obtained by normalizing the similarity map.but use exp() while in decriptor loss use softmax().
it is a careless mistake?or i misunderstood.
Thanks
Hi author,
Thank you for your amazing work.
I'm trying to export the ALIKE models to ONNX for inferencing on edge-devices. However, the some operation in the model are not supported to convert to ONNX, including : grid_sampler, argsort.
Have you tried converting the model to ONNX before, and was it successful, if yes, could you please guide me to export to ONNX ? Many thanks in advance !
Best regards,
Michael
Hi Shiaoming,
Did you plan to release the training code ?
I read this, 'We will publish the training code for ALIKED (the subsequent work of ALIKE, which we are working on). Then you can refer to the training code of ALIKED, they have the same training pipeline.'.
But I see nothing on ALIKED repository ?
Thank you.
Upon examination of your code, I noticed the existence of a parameter named "sub_pixel," which is set to False by default. Upon further investigation, I discovered that enabling this parameter by setting it to True can result in improved performance. I am interested in understanding whether there are any potential drawbacks to enabling this parameter during inference. Furthermore, I would like to inquire about the rationale behind disabling this parameter by default.
Hello
I have no idea about how to calculate the Matching Score in the code.
Any help would be appreciated.
This is a very interesting work, that achieves some impressive results. I am very interested in adapting ALIKE to my needs. Would you be willing to share/publish the code used for training the network?
when i run hesq/eval.py, i got all MMA@3 >MMA@5.
is the code wrong?
and
for code for thr in range(1, 4):
thr
should output 1,2,3, not 1,3,5
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.