xiaoaoran / synlidar Goto Github PK
View Code? Open in Web Editor NEWSynLiDAR: Synthetic LiDAR sequential point cloud dataset with point-wise annotations (AAAI2022)
License: MIT License
SynLiDAR: Synthetic LiDAR sequential point cloud dataset with point-wise annotations (AAAI2022)
License: MIT License
will the code be available in the near future?
Thanks for your awesome work. Now I am trying to download the dataset using the provided download.py.
However, as shown in the above figure, the size of all downloaded subsets could not exceed 5.9 GB, so I want to if there is any constraint on the server or any other things I should check.
Thanks
Dear @xiaoaoran,
I would like to start by expressing my appreciation for your work. It is interesting and inspires the research community for UDA tasks.
I have downloaded the dataset and found out that the Pose (the transformation matrix between local to global coordinate systems) information regarding the Ego-vehicle/Lidar Sensor is missing. Can you please point me where it is stored?
Thank you.
Looking forward to hearing from you soon.
Thank you for the interesting work.
Would you like to share the code for PCT? Especially, the code for the appearance translation module and the sparsity translation module. Thanks!
Hello,
I just found that 04.02 is missing on Baidu driver, could you please check this part?
Hi, Aoran Xiao.
Firstly, thank you for your brilliant work! I see that you have given an example of class mapping from synlidar to semantickitti. And could you share the YAML file of semanticPOSS with me too? Please help.
I noticed on you paper that "Detailed descriptions about the rendering model and experiments are presented in Appendix" but I can't find the appendix nowhere. Could you kindly provide some more information about that?
Thanks!
Could you provide a list file listing all the files in the SubDataset and their paths in the FullDataset, which makes a fair comparison more convenient. Thank you!
Thank you very much for the interesting work and providing the dataset.
I was wondering, which LiDAR sensor you simulated (if you had a specific selected) when generating the dataset or if you have the specifications (like angles, number of beams , number of points per beam) of the sensor that you simulate.
Thank you very much again.
Best,
Dear authors,
thank you very much for your very interesting work.
In my actual project I would need to name each class index but, unfortunately, I found it is missing a mapping between class indexes [0, 31] and class names [road, .., table].
Can you please provide the mapping between index-name?
Thank you in advance!
Hello,
Thanks for your awesome work. Will you consider releasing this dataset on google/Baidu cloud? We found it difficult to download such a large dataset from the current server.
Thanks.
Hi, Aoran Xiao.
Thank you for your brilliant work.
I see that "-- SubDataset: uniformlly downsampled dataset (about 24GB), this is the dataset that we used in Paper. You are recommend to use this smaller dataset for faster experiments." in readme file.
To fairly compare with your method, I would like to confirm that all the experimental results in your paper "Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation" use SubDataset?
Hi, Aoran Xiao. First of all, thank you very much for the previous sharing of the mapping file.
But I have a question. Why is the mapping categories of SemanticPoss in the file inconsistent with the categories given in the paper?
Thank you for the great work and datasets! I'm wondering will you also release all the unreal environments you have created?
Hi!
thanks for the dataset!
Each sequence is provided in the sensor frame therefore it is impossible to accurately register all the frames. Are you going to provide calibration files with affine transform matrices for registering the frames?
Thanks in advance!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.