We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultaneously preserving privacy via multi-party computation. More information can be found on the project website https://visualmpc.cs.columbia.edu/.
To generate new training datasets:
bash run_gen_dataset.sh
To test existing models:
bash run_test.sh
Models can be downloaded from https://drive.google.com/drive/folders/1f7FMLwfXQzNSNLOVdWfSi2sYYZarSbl3?usp=sharing and put under the root directory of the file.