Comments (2)
Thanks for your interest in our work.
I didn't notice this issue before and thanks for pointing it out.
After inspecting the data, I found out this issue could be mainly due to the unsmooth "groundtruth" poses of the KITTI dataset.
As you can see in the above figure, the red trajectory is the one estimated by PIN-SLAM and the black trajectory is the "ground truth" GNSS-INS pose provided by KITTI. There's a jump on the Z-axis for the black trajectory. A similar situation can be found at the beginning of KITTI sequence 08. In some other sequences, you can clearly see there is some inconsistency in the trajectory at a revisited region on the Z-axis.
I suspect this unsmooth "groundtruth" poses is the cause of the unexpected artifacts. With the smooth pose estimated by PIN-SLAM, the artifacts would not appear and most of the dynamic objects can be removed by the free space sampling via raycasting.
I hope this help to answer your concern.
from pin_slam.
Hi @YuePanEdward, Thanks a lot for your reasonable replay! I believe it does be the true reason resulting in these artifacts.
from pin_slam.
Related Issues (20)
- Noisy Mesh HOT 4
- How many GPU memory need for generate a full scene mesh video like [demo_kitti00.mp4 ] ? HOT 1
- Attitude drift after making a turn in custom dataset HOT 12
- Difficult to operate at the sensor frequency in kitti 00 HOT 2
- About time consumption HOT 2
- How to use Replica dataset HOT 2
- signal frame HOT 2
- odometry evaluation HOT 4
- CUDA error even when using cpu yaml HOT 1
- question about parameter correct_deg:0.195 in run_kitti.yaml HOT 2
- Would the training code be released? HOT 1
- issue about mesh HOT 5
- LiDAR points and Visual RGB HOT 2
- Have individual data loader for each dataset HOT 1
- Add pure-localization mode
- Have the values of `local_neural_points` been modified between being selected from and reassigned to global neural points? HOT 2
- torch.cuda.OutOfMemoryError: CUDA out of memory HOT 4
- About the VBR dataset HOT 1
- How to understand the stability of neural points? HOT 4
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 pin_slam.