Codebase of Master Thesis: Application-oriented Investigation of Domain Adaptation for 3D Object Detection in Automotive Point Clouds
You may refer to INSTALL.md for the installation of 3DTrans.
-
Please refer to Readme for Datasets to prepare the dataset and convert the data into the 3DTrans format.
-
Training and testing can be started with the train.sh and test.sh
-
Zenseact dataset demo can be found in tools/zod_demo.py
- Our
3DTranssupports the sequence-level visualization function Quick Sequence Demo to continuously display the prediction results of ground truth of a selected scene.
- Our code is heavily based on OpenPCDet v0.5.2. Thanks OpenPCDet Development Team for their awesome codebase.