Official implementation of the paper "Progressive End-to-End Object Detection in Crowded Scenes"

Face recognition implementation is capable of recognizing faces with occlusion, this includes faces wearing masks.

A awesome project for person re-id. There are re-implements of PCB, MGN, MDRS(ours), PGFA, Pyramidal and HOReID.

The official code implementation for SynTable - A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes

Noise Aware OSTrack

CurveTopia tackles shape detection and completion, featuring regularization and occlusion tasks. The Regularisation folder contains the regularization task, and the master_folder holds Jupyter notebooks (.ipynb) for Algorithms 1 to 4 on occlusion. The Streamlit app integrates all solutions for interactive use.

A Tracking Framework for MOT Challenge

Occlusion and Multi-pose Face Recognition Dataset

To observer a target in the environment, Drone has to find out a pose that can view the target and also does not collide with the obstacle. Octomap is used for checking whether the pose is available.

Some of the work done during the winter research intern at IIST, Trivandrum