AI Agent Skills

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning | Official repository

MonoLayout: Amodal Scene Layout from a single image

Face-recognition using Siamese network

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

:gem: "Marker-less Augmented Reality" with OpenCV and OpenGL.

Implementation of the paper "No Reference Image Quality Assessment in the Spatial Domain" by A Mittal et al. in OpenCV (using both C++ and Python)

ROS packages of the Autonomous landing system of a UAV in Gazebo

TUI tool for ROS

A fairly in-depth tutorial for the Point Cloud Library (with ROS integration notes!)

Jupyter Notebooks with Deep Learning Tutorials

Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

Dataflow system for building self-driving car and robotics applications.

:pencil: Exam bubble sheet scorer. Created with OpenCV and Python.

Generating automatic trimap through pixel dilation and strongly-connected-component algorithms

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

[ICLR2025] Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion