#Depth Estimation

Browse a detailed and continuously updated collection of papers on monocular 3D object detection from 2016 to 2024. This repository showcases the latest methods such as complementary depths and pseudo-labeling frameworks including MonoCD and UniMODE. Access exhaustive methodologies, publication links, and implementations to gain insights into improving detection accuracy in autonomous driving and AI applications. Stay informed on the evolving technologies within the industry.

The model delivers a unified solution for flow, stereo, and depth estimation, earning top ranks on Sintel, Middlebury, and Argoverse. Building on GMFlow, it offers diverse pretrained models for 3D perception tasks, with installation via Conda or pip. It includes comprehensive evaluation scripts and training guides for reproducing and extending its capabilities, facilitating precise optical flow, disparity, and depth outcomes.