Comments (2)
Hi @xingruiy,
you can modify "num_points" in the config files:
https://github.com/JuanDuGit/DH3D/blob/master/models/local/config.json
https://github.com/JuanDuGit/DH3D/blob/master/models/global/config.json
After you change this number to x, the network will assume it to be the size of all the input point clouds. Each input point cloud will first be sampled using a voxel grid. If the number of points is smaller than x after sampling, the point cloud will be padded; if larger than x, only x points will be used.
So the pre-trained model can be directly applied on point clouds with different sizes. However, the performance is not guaranteed. The density of the point clouds will influence the local descriptor, and this will further influence the global descriptor. Additionally the global descriptor is also correlated to the coverage of the point clouds.
Hope this is useful.
from dh3d.
@rui2016 Many thanks!
from dh3d.
Related Issues (12)
- Monocular Relocalization HOT 1
- Input & output node names HOT 4
- hello, I meet a problem.I use RTX4080,with docker and cuda10.1, tf1.9.0,and I meet the flowing issue: HOT 1
- Hello,It's a nice work,can the process of training be resumed?I meet the warning" If you want to resume old training, either use `AutoResumeTrainConfig` or correctly set the new starting_epoch yourself to avoid inconsistency.",But I don't know how to change the world
- local feature detector HOT 1
- what kind of graphics driver do you use? HOT 2
- Evaluation results are different from the paper HOT 2
- Question about model runtime and relocalization process HOT 1
- Why are there two separate models for local/global descriptor? HOT 5
- Error running code HOT 1
- Point Cloud Retrieval for DSO 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 dh3d.