Comments (7)
@nawara72
Sure thing! I can think of 2 likely reasons for the "fuzzy"ness:
1- Might want to play around with the point_size
of the visualization (with open3d
, you can change point size interactively with +/- shortcuts in the visualization; withplotly
, you can specify point size by pointclouds.plotly(0, point_size=2)
)
2- In case of plotly
visualization, we downsample the pointclouds before visualization because plotly visualization can be slow/break with large pointclouds.
You can use open3d
for saving a pointcloud:
import open3d as o3d
o3d.io.write_point_cloud("pointcloud.ply", pointclouds.open3d(0))
from gradslam.
Great thanks for all your great support and help and will definitely share any output that I get from realsense
Thanks and take care
from gradslam.
Hi @nawara72,
Thanks for your interest! Would it be possible for you to share a sample output reconstruction so we can assist you better?
from gradslam.
Hi @nawara72,
The sequences
argument for TUM
expects something like:
dataset = TUM(basedir="C:/Users/cv/Documents/gradslam_data/TUM/", sequences=("rgbd_dataset_freiburg1_xyz", ), seqlen = 10)
where you specify a tuple of sequnce names which you want to load. I'm also curious if you can share a sample output reconstruction.
Here is a working example of PointFusion
on TUM/rgbd_dataset_freiburg1_xyz
in Google Colab:
https://colab.research.google.com/drive/1uxjEJI5B2yJJDG3SxoAagH9uEuT67rXC?usp=sharing
from gradslam.
Thanks for the quick reply and for sharing the TUM example code, really appreciate it. After running the code you shared, I got similar output to when I ran it. I just thought the output point cloud would be more sharper (ie not so fuzzy).
Is there any way I can write the pointcloud to a file (eg ply) to look at it in more detail.
Thanks and thanks again for all your efforts and for sharing
from gradslam.
Great will try that soon 👍
Also hoping soon to try and save some rgbd data from realsense and pass it to gradslam. Do you envisage any issues with that?
Thanks again
from gradslam.
Excited to see what that will look like! Can't envisage any issues at the moment, but if you find any bugs/unexpected behavior with the library or can think of extra features which would help your use case, feel free to open up another issue and we'll look into it!
from gradslam.
Related Issues (20)
- Chamferdist installation error HOT 2
- Questions about gradLM HOT 4
- How to run gradslam with the TUM dataset? HOT 2
- Question about step by step method! HOT 2
- Example of Training end-to-end for a simple task that includes mapping
- How are loop closures supported in GradSLAM? HOT 3
- TUM/ICL Poses HOT 2
- Question about using ScanNet HOT 1
- To save the pointcloud once generated. HOT 1
- Is the Poses Data Actually Used in the SLAM Process?
- How is RGB used here? HOT 1
- Usage of multiple RGBD sensors as input HOT 3
- How do gradslam learn anything using the differentiable modules? HOT 1
- Reproducing `Analysis of Gradinets` Results HOT 1
- how the jacobian is derived? HOT 1
- No matching distribution found for open3d==0.10.0.0 HOT 4
- not compiled with GPU support error in chamfer.py when using gradicp HOT 2
- How can I run these codes?
- how to use it in customer dataset
- Unable to use distortion in ConceptFusion 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 gradslam.