Comments (7)
Hi @hzhsdie,
You can use it for your research!
First, you should follow here to extract a set of yoho features on each point cloud.
Then, you can follow here to use SGHR on your own dataset.
Registering 10 scans will be quite fast (might be a few minutes or less).
Yours,
from sghr.
Hi @hzhsdie, You can use it for your research! First, you should follow here to extract a set of yoho features on each point cloud. Then, you can follow here to use SGHR on your own dataset. Registering 10 scans will be quite fast (might be a few minutes or less).
Yours,
I'd like to ask, what is the Rotation.npy file needed when extracting YOHO features? How can I obtain this file? Also, if I only have multiple point clouds, can I achieve obtaining the registered point cloud by just inputting the point cloud files? Looking forward to your reply thank u!
from sghr.
Hi @Tcode8,
The Rotation.npy file is the group rotations required for YOHO feature extraction.
For the second question, the answer is yes. No other files are needed.
Yours,
from sghr.
Hi @Tcode8, The Rotation.npy file is the group rotations required for YOHO feature extraction. For the second question, the answer is yes. No other files are needed.
Yours,
May I ask what content is contained in the 'Rotation.npy' file and how can I obtain this file?
from sghr.
Hi @Tcode8,
This file contains 60 rotations of the icosahedral group. You can directly use the one at https://github.com/HpWang-whu/YOHO/blob/master/group_related/Rotation.npy rather than create one yourself. This file is universal for feature extraction on any point cloud.
Yours,
from sghr.
Hi @hzhsdie, You can use it for your research! First, you should follow here to extract a set of yoho features on each point cloud. Then, you can follow here to use SGHR on your own dataset. Registering 10 scans will be quite fast (might be a few minutes or less).
Yours,
Thank you very much for your suggestion, I have implemented the registration of local data, however I can't seem to visualize it, how do I view the final registration result? What do the saved pose.txt and pre.log files refer to?
from sghr.
Hi @hzhsdie,
I have uploaded a script for result visualization. Now you can view the registration result with:
python visual.py --dataset 3dmatch
Yours,
from sghr.
Related Issues (20)
- setting up knn_search HOT 1
- results visualization HOT 2
- How to generate YOHO_desc with my own data? HOT 1
- Why training takes several hours, how to speed it up HOT 3
- Question about the comparison methods HOT 2
- Is ther any way to test the trained SGHR model on my own data without the Minkowski Engine HOT 1
- Test.py bug HOT 2
- 计算统一坐标系时遇到问题 HOT 2
- correlation between point cloud resolution and the parameter voxel size in demo.py HOT 2
- On the parameters that need to be adjusted for testing with local datasets HOT 1
- About the RANSAC substitution in pairwise registration HOT 1
- 对3dmatch数据集test时结果波动大 HOT 3
- Computation of the translation synchronization HOT 3
- How should I train my dataset? HOT 3
- Why is the GPU occupancy rate during training very low, only 10% HOT 3
- What is the role of gt.info and test_3dmatch.pkl?Also bug report. HOT 2
- Some question about the paper and code HOT 2
- How to obtain key point text files for point clouds HOT 8
- How to test on my own dataset? HOT 3
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 sghr.