Comments (4)
Thanks for your interests! These different variables are generated by warping different maps (feature map, input image map, etc) based on the same motion flow field estimated by our network. They are concatenated together as the input of the decoding network for predicting the RGB value at the input coordinate (x, y, t).
from videoinr-continuous-space-time-super-resolution.
Thanks for your answer. And here are some other Qs, thank you very much!
- why did you estimate two flow in the work?
- where is the process of SpatialINR after warping in code, is SpatialINR “feat_imnet” in code? But I didnt find the usage after warp? So how did you do this process?
from videoinr-continuous-space-time-super-resolution.
- At the beginning we want to apply a bi-directional architecture for the motion flow (flow t->0 and flow t->1), and we applied some explicit constraints on the network to learn such bi-directional flows. After extensive experiments we found that learning two flows without constraints yields better results, comparing with one single flow or two flows with bi-directional constraints.
- feat_imnet is used to generate the continuous feature corresponding to the input 3D coordinate (x,y,t).
from videoinr-continuous-space-time-super-resolution.
Thanks for the good Research.
But I have similar problem understanding the function of TemporalINR and calculating motionflow.
- How TemporalINR which is SIREN could get motion flow as output?
- Also, in paper you mentioned that 'we generate two independent flows for the motion flow field, and concatenate corresponding warped features'. What is the two independent flow ? Is it flow from frame I_0 to frame I_1 frame flow and frame I_1 to frame I_0 frame?
from videoinr-continuous-space-time-super-resolution.
@zychen-ustc Hello! Also thank you for great research and code!
any comment on above question?
Is 'encode_imnet' is SpatialINR for warpped spatial coord?
from videoinr-continuous-space-time-super-resolution.
Related Issues (17)
- Cannot run the demo: missing files and old dependencies HOT 3
- 请教关于代码的一些问题 HOT 1
- The cpu memory usage will continue to increase during training
- 测试遇到的问题
- License information
- Evaluation Procedure
- A typo in paper? center frame is 1 5 9 rather than 1 4 9 ?
- Evaluation on Y channel or RGB channels
- Hello, I am very interested in your research. Will the training code be released HOT 1
- 在CUDA版本11.1,GPURTX3070Ti上的安装问题 HOT 2
- training cost HOT 2
- Unknown CUDA arch 8.0 or GPU not supported in DCNv2 setup HOT 3
- Is it the last release that I can train the model? HOT 1
- New Super-Resolution Benchmarks
- High resolution model HOT 2
- Testing scripts of VideoINR HOT 9
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 videoinr-continuous-space-time-super-resolution.