Comments (4)
Yes, you can do that! The mask_c0 should have the same shape as that of feat_c0, which is 1/8 of the input image shape.
And may I ask why do you want to try this? I think inference without mask is more convenient, and they should have no difference😂
from loftr.
Thanks, I’ll try that.
There are cases where there is a small overlap between the two images or the images are cropped, in these cases I’ve noticed that it is harder for the NN to match the correct features or somethings it finds features outside of the cropped area, where there are zeros. So I try to make it consider only part of the images plane.
from loftr.
Oh, I see. I think you could also use the cropped CNN feature maps instead of using masks. That will save you a lot of GPU memory😃.
from loftr.
Thanks, I’ll try that.
There are cases where there is a small overlap between the two images or the images are cropped, in these cases I’ve noticed that it is harder for the NN to match the correct features or somethings it finds features outside of the cropped area, where there are zeros. So I try to make it consider only part of the images plane.
I can also confirm this. If anyone else has similar problem, where there is a small overlap between images (like 20% - 40%), create a mask of that overlap region, resize it 1/8 to the shape you pass to model. I sometimes get even 10x more control points
from loftr.
Related Issues (20)
- Tensorboard visualization - are the indices correct?
- About train with fp16
- About the dataset indices of Megadepth HOT 2
- How to train the model for HPatches
- train model for image matching
- training on custom dataset HOT 4
- Can the model be limited to detecting key points in a region of interest?
- h5py can't read data
- meet an error when training loftr: EOFError: Ran out of input HOT 3
- image size
- Bug found in supervision process
- main_cfg problem
- How to train LoFTR on custom dataset?
- megadepth_indices下载不下来 HOT 1
- How to get image feature maps from the pretrained model?
- My dataset is only RGB, can I use it for training?
- ScanNet Training Pairs
- File "h5py\h5f.pyx", line 96, in h5py.h5f.open OSError: Unable to open file
- COLMAP dumps for Megadepth 1500 dataset
- to reproduce the training,have to download MegaDepth_v1?199G dataset? HOT 1
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 loftr.