Accepted to IEEE Robotics and Automation Letters (RA-L) April 2024, presented at IEEE Conference on Robotics and Automation (ICRA) May 2025

paper: IEEE Robotics and Automation Letters (RA-L) video: YouTube

PreFixer learns unsupervised a universal transformation between dataset distributions. The difference between these dataset distributions are a result of hardware versioning between sensors. This transformation should preserve several properties of the original dataset:

1. The prediction of the base model.
2. The structure and features present in the image.

Problem setup

Input and output of trained PreFixer

pip install -r requirements.txt cd training python train_lenscoder.py <path-to-dataset>