Comments (2)
Hello!
The network was trained on a single, and very specific, domain: outdoor images captured by pedestrians.
We tried "cross-domain" matching, but it was done between indoor (ScanNet) and outdoors (Map-free). We show in the supplementary that the network generalized fairly well there, but both domains are still visible light images.
MicKey has not seen any such examples, eg, infrared images, during training and I would not be surprised if it does not work very well.
from mickey.
Thank you for your answer. I would like to ask if the input is an image pair, one as a reference image and the other as a source image, can the source image be converted to the perspective of the reference image through the Mickey model? Similar to solving the transformation matrix between the two? Please tell me how to implement it in the code, because the demo seems to be more inclined to output the depth map and the confidence score map, but it does not give me the conversion result. Looking forward to your reply!
from mickey.
Related Issues (17)
- visualization HOT 13
- Query regarding the Multi-frame Map-free benchmark HOT 4
- KeyError in backward_step Method Due to Missing depth0 in batch Dictionary HOT 1
- Question about the evaluated results HOT 2
- Errors in multi-gpu training HOT 1
- Predicting X and Y coordinates directly. HOT 2
- ScanNet datasets weights and dataloader HOT 1
- Minor bug in e2eprobabilisticprocrustes HOT 1
- Training cost HOT 1
- A naive question about depth prediction HOT 3
- How to perform image pair matching HOT 2
- Obtaining pose confidence measurements HOT 3
- Basic question on resizing images HOT 3
- How to get overlaps.npz in customer datasets HOT 4
- How to get poses for more than 2 images (in the same coordinate world) HOT 3
- Run on images from different cameras? HOT 2
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 mickey.