Comments (3)
Hi! I appreciate your interest! I am not sure what the ``depth'' here refers to. Does this stand for depth estimation? If so, you can also train your depth estimation models via DEQ on your own datasets! If you hope to calculate the depth directly, It probably needs more geometric features like disparity or configurations of the camera.
Please feel free to ask if you have additional questions.
from deq-flow.
@Gsunshine
thank you for your reply
Depth means whether the true distance can be calculated by flow_pr(Depth = baseline*focal_length / disparity). If I input not the picture data of continuous frames but the left and right purpose data, can I get the correct flow_pr or can DEQ be trained on binocular data?
I don't know much about RAFT, but I've seen some of the left-stereo model. I am interested in DEQ's update module. But there are iterations, and one of the iterations of left-stereo includes a CORR module, and I wonder what the difference is between the two?
from deq-flow.
It seems that I didn't understand optical flow estimation and depth estimation!
from deq-flow.
Related Issues (8)
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 deq-flow.