Comments (5)
Hi,
- We used color images only from Camera2, which corresponds to 'image_2' folder in the original dataset. The Camera2 was mounted in the center of the vehicle, which turns out to be sufficient for this task.
- The results presented in the paper are the ones with no prior preprocessing since we want our method to operate on raw point clouds. Moreover, we did not observe any significant difference when removing the ground plane. However, I suspect cropping a cloud could slightly improve the results.
- We used only x,z to calculate distances (2D).
from minklocmultimodal.
Thank you for the comment. That was very helpful!
from minklocmultimodal.
I have one more question. I'm trying to run it with the KITTI dataset, but if I put it as is, the number of points does not decrease with ME.utils.sparse_quantize. Is this correct? Or is it correct to shift and rescale to zero mean and [-1, 1] like the existing dataset?
from minklocmultimodal.
No, there is no need for that. You can simply perform quantization without rescaling. For Kitti dataset we set quantization step=0.25.
from minklocmultimodal.
Oh, I understand. Thank you again!
from minklocmultimodal.
Related Issues (20)
- Question about how to generate batches? HOT 2
- loss become nan during training HOT 8
- Question about the model structure HOT 3
- How to normalize the RobotCar pointcloud data to [-1,1]? HOT 2
- How to evaluate on KITTI dataset? HOT 3
- Question about pointcloud data HOT 5
- Question about the code
- Bug in lidar2image_ndx generation for val queries HOT 1
- the Oxford Robotcar Dataset unavailable HOT 2
- questions about training HOT 2
- Something is wrong with the mapping file lidar2image_ndx.pickle HOT 7
- The pre-processed RobotCar images are unavailable HOT 2
- Oxford Dataset RGB Image Process HOT 5
- RobotCar images HOT 2
- MinkLoc++ (RGB-only) generation HOT 4
- bin file data format HOT 2
- How about the MinkLoc++ inference efficiency compared to MinkLoc3D HOT 4
- About how to get image to lidar dataset? HOT 4
- Question about the code- "positives_masks" & "negatives_masks" HOT 2
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 minklocmultimodal.