monodepth2
Explore Monodepth2's PyTorch-based reference implementation for advanced depth estimation. The project methodically outlines dependency setups, guides on predicting scaled disparities, and furnishes ready-to-use pretrained models. Detailed instructions for custom dataset training, model finetuning, and KITTI dataset evaluation are included, alongside support for multiple training modalities including monocular, stereo, and combined approaches, catering to diverse research requirements.
