Omkar Chittar's Projects
In this project, the A* path planning algorithm was implemented on a point robot for helping it navigate through an obstacle filled space.
Working of Autoencoders and its implementation in PyTorch
Finding all the possible states of the 8-Puzzle starting from the given initial state until the goal node is reached. States being unique. β’Using the initial state of the puzzle, performing different moves in all the directions to generate new states. Using BFS to reach the goal. Back tracking for solving the problem
SvelteKit blog
This project aims to estimate camera pose using homography for a given video. Steps involved are designing an image processing pipeline to extract paper's corners, computing homography between real-world points and pixel coordinates of the corners, and decomposing the homography matrix to obtain rotation and translation parameters.
Design and Simulation of LQR and LQG Controller for Crane System
In this project, the Dijkstra's path planning algorithm was implemented on a point robot for helping it navigate through an obstacle filled space.
Daily DSA
Modelling and SImulation of a mobile robot in Gazebo
Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.
Generative Adversarial Networks on MNIST and Human Faces Dataset
Calculates the final course grade for ENPM611
This project involves stitching together four images taken from the different camera positions to create a panoramic image. The goal is to seamlessly merge the images together so that the resulting panoramic image looks like a single, continuous image.
With INR, we parameterize some signal (in our case images) with a neural network (in this assignment, we will use a basic feed-forward network).
Color based image segmentation
Lane Detection using classical approach and a deep learning based approach
Controlling a 7 DOF manipulator from the panda gym reacher environment using DDPG
Mapping based on Monte Carlo particle filter with lidar scan, accelerometer and gyroscope data.
Perform Differentiable Volume Rendering: Ray sampling from cameras, Point sampling along rays. Optimizing a basic implicit volume, Optimizing a Neural Radiance Field.
Sphere Tracing. Optimizing a Neural SDF. VolSDF. Phong Relighting.
Simulation of an obstacle avoidance turtlebot3 based on lidar data
Estimating Ground Surface Normals and Fitting Surfaces to Noisy LIDAR Point Cloud Data
Implementing a PointNet based architecture for classification and segmentation with point clouds. Q1 and Q2 focus on implementing, training and testing models. Q3 asks you to quantitatively analyze model robustness.
This repository contains the Pytorch code for human pose estimation using the CAREN dataset.
Learning the basics of rendering with PyTorch3D, exploring 3D representations, and practicing constructing simple geometry.
Using Google Gemini to generate quizzes from any sets of pdf files