Comments (5)
Currently, I disable the usage of the non-local flow for a faster speed. But I do provide the non-local implementation in get_flowNN.py
so it should be easy to use.
Your interpretation in consistencyThres is correct. If we are too strict with it, the algorithm will prefer the per-frame inpainted content to the propagated content, tho the quality may not be very good. If the constraint is too loose (inf), the algorithm will propagate everything. The result is smooth but probably incorrect.
If you really care about the correctness, I'll suggest using consistencyThres=5. The reason I set the default to be inf is that
1> it speeds up the process, and
2> our seamless blending will make sure to smoothen the propagated content so that the final result is plausible (even though it is not correct).
Hope this helps!
from fgvc.
Thanks! Your answer really helps!
from fgvc.
One more question, please. Is the same set of parameters recommended for the fixed region removal task, too?
from fgvc.
Yep, I use the same set of parameters.
You can always start with consistencyThres=5 and then adjust. If you enable seamless blending, I'll suggest using a looser threshold, i.e. 99.
Sorry for the late reply. Let me know if you have other questions.
from fgvc.
@gaochen315
if the mask part is small, the consistencyThres will be small ?
from fgvc.
Related Issues (20)
- ' --Nonlocal ' in video_completion.py results in error HOT 2
- Object removal task evaluation code HOT 3
- RuntimeError: Error keeps saying "to have 3 channels, but got 4 channels instead" HOT 1
- The implementation of the homography warp before optical flow calculation HOT 4
- Inpainting doesn't seem to clean up intermediary files HOT 2
- server for weights.zip and data.zip seems unreachable HOT 5
- 对于较少背景移动时,去除文字水印,会出现填充拖影问题 HOT 1
- How can I train a new model on a different dataset? HOT 4
- Same problem result of '--Nonlocal' (as issue #52) HOT 2
- Where can I read about all those parameters such as edge guide, mixed precisions and so on? HOT 1
- Code Error in non-local optical flow concatenation HOT 1
- RAFT Model HOT 1
- edge_guide flag HOT 1
- test question HOT 2
- Inference is not as accurate as the provided video samples HOT 4
- Evaluation Metrics HOT 2
- code question
- How to train the network? HOT 1
- Please Large FOV colab
- Dependencies can't be installed in colab
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 fgvc.