Comments (4)
The weights we provide were pre-trained on images from the 1M distractor images of https://github.com/filipradenovic/revisitop, then fine-tuned on MegaDepth.
Do you have examples of pairs of images of HPatches where it does not work so well? It should have a decent performance there, except for images with large rotations (eg > 45 degrees).
from gluestick.
I tested that in the v_boat case of Hpatches, image 1 doesn't match image 5 very well, they happen to be largely rotated
from gluestick.
Yes, image 5 has almost a 90 degrees rotation compared to image 1. GlueStick was only trained for small rotations, so it cannot cope with such big rotations. When you know that your application will have rotation, you can always rotate one of the two images by 90 degrees several times and match the first image with the second one rotated at 0, 90, 180 and 270 degrees.
from gluestick.
Ok, I will go and try to do some rotation pre-processing, thanks for your patience
from gluestick.
Related Issues (20)
- A question HOT 3
- Inference speed HOT 2
- About FPS and real-time performance HOT 2
- A question about dual-softmax HOT 2
- Integration to HLOC or COLMAP? HOT 3
- match confidence HOT 2
- Question about reprojection error HOT 3
- Guidance Needed: Mapping Single Points Using Homography for Images of Different Sizes HOT 6
- Another method instead of Homography estimation HOT 1
- There is no setup.py for "pip install -e ." HOT 3
- Memory not releasing issue HOT 2
- Can GlueStick export onnx? HOT 3
- training HOT 4
- How to only use lines/points? HOT 3
- pytlsd causes memory leak HOT 2
- can you open source your evaluation code? HOT 6
- How to only use points? HOT 2
- How to obtain the four parameters lines0, lines1, lines_junc_idx0, lines_junc_idx1 ? HOT 2
- Training code HOT 12
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gluestick.