Comments (1)
Hey,
the constD trick is a very crude tool that's only justified if you have no information about the correct depth. In your case, there is quite a lot of information available (even if it is sparse). I would try to create dense maps from your sparse maps using interpolation / hole filling methods, and train with those dense maps. Even if they are not perfect, training stage two (optimizing reprojection error) will probably fix errors in many places.
As a first quick and dirty check, you could just do nearest neighbor interpolation of your sparse depth (assign the depth of the nearest pixel with a value). Maybe do early stopping in training stage one to avoid overfitting to these interpolated depth maps.
Kind regards,
Eric
from lessmore.
Related Issues (20)
- How many time did you spend on testing? HOT 1
- How many time did you spend on testing? HOT 1
- Camera calibration matrix of Cambridge landmark HOT 2
- Mapping Depth to RGB & Pose Correction HOT 3
- Scene Pose vs Camera Pose HOT 1
- Training Time issue HOT 1
- projectPoints vs project HOT 2
- Calculate target scene coordinates using 3D model HOT 1
- is there any way to improve accuracy HOT 1
- is there any way to improve accuracy HOT 1
- --
- Why i can't get the Graduated Colors by using convertForDisplay function in util.cpp? HOT 3
- testing results HOT 5
- questions about utilizing a scene coordiante heuristic based on a constant depth assumption HOT 4
- Inconsistent accuracy - low angular errors and high translation errors for a new dataset HOT 2
- The intrinsic paramters of Cambridge dataset HOT 1
- missing files in the dataset HOT 1
- Is there a way to produce the predicted camera poses instead of test evaluation? HOT 1
- A Make Problem! HOT 2
- batch size 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 lessmore.