I am actively looking for full-time positions in Machine Learning, Robotics, Self-Driving, AR/VR, Computer Vision.

Reach out on LinkedIn or Email me if you or someone you know is hiring 🙂

👋 Hi, I’m Aditya Wagh

NYC-based Roboticist working on Machine Learning + Computer Vision and Robotics.

Interested in Augmented and Extented Reality (AR/XR), Self-Driving (Pereption, SLAM and Control), 3D Reconstruction - Structure-from-Motion, Photogrammetry, Neural Rendering & NeRF, Gaussian Splatting, Distributed ML, ML Inference
Exploring - LLMs, VLMs, AI Agents, Embodied AI and Robot Learning (Imitation Learning, Behaviour Cloning, Vision-Language-Action Models, Reinforcement Learning)

I hold a MS in Electrical Engineering from New York University (NYU) and a B.Eng (Honors) Electrical Engineering from BITS Pilani.

Always eager to learn new things. Always open to discussions and collaboration. Feel free to reach out to me via: LinkedIn, Email or X/Twitter (Open DMs)

🛠️ Tech Stack

Experienced

Learning

Projects

Below is a list of my notable projects. Feel free to have a look at whatever you find interesting!

SuperSLAM: Open Source Framework for Deep Learning based Visual SLAM

SuperSLAM

SuperSLAM: Open Source Framework for Deep Learning based Visual SLAM

Code

Pose estimation pipeline to enable 3D reconstruction using Local Feature Transformer (LoFTR)

Deep Image Matching using Local Feature Transformer

Pose estimation pipeline to enable 3D reconstruction using Local Feature Transformer (LoFTR)

Code

Optimal state estimation using extended & unscented kalman filter implemented using MATLAB

State Estimation of a Drone by Visual-Inertial Sensor Fusion

Optimal state estimation using extended & unscented kalman filter implemented using MATLAB

Code

Benchmarking of LiDAR 3D Object Detection networks (VoxelNet, PointNet++, PointPillars) on KITTI Dataset.

3D Object Detection in LiDAR Point Clouds

Benchmarking of LiDAR 3D Object Detection networks (VoxelNet, PointNet++, PointPillars) on KITTI Dataset.

Code

A visualization in reduced dimension to show how autoencoders learn features in the Fashion MNIST dataset.

Dimensionality Reduction using Convolutional Autoencoders

A visualization in reduced dimension to show how autoencoders learn features in the Fashion MNIST dataset.

Code

Fast, Parallel implementation of the RANSAC algorithm to segment a plane in a point cloud.

Fast Plane Extraction from a 3D Point Cloud

Fast, Parallel implementation of the RANSAC algorithm to segment a plane in a point cloud.

Code

A convolutional neural network for multi-task visual damage assesment.

Post-Earthquake damage assesment using FCNs

A convolutional neural network for multi-task visual damage assesment.

Code

Relative Pose estimation using OpenCV

Two-View geometry based pose estimation

Relative Pose estimation using OpenCV

Code

Convolutional Neural Network for detecting power cables.

Power cable detection using Deep Learning

Convolutional Neural Network for detecting power cables.

Code

A modification in a RNN unit that reduces redundant computation.

Variable Computation in RNNs

A modification in a RNN unit that reduces redundant computation.

Code

A tango inspired dark theme for Visual Studio Code.

Tango+

A tango inspired dark theme for Visual Studio Code.

Code

A simple and elegant Jekyll theme for portfolio pages

Clean Portfolio

A simple and elegant Jekyll theme for portfolio pages

Code