P

pose estimation

MF-3DPnP is a non-learning-based pipeline for robust geometric pose estimation using monocular vision, sparse or dense depth, and optional inertial measurements (IMU). It is designed as a strong baseline for comparing pure geometric approaches to modern learning-based methods, with a particular focus on aerial and robotics datasets (such as EuRoC and TUM-VI).

Reads specialized markers to estimate pose and then rescales the result for 3D models for different proportions.

A dockerized web application serving results of resNet50-based pre-trained DensePose model