omkarchittar
Computer Vison | Pattern Recognition
University of Maryland, College ParkCollege Park, MD
Pinned Repositories
Image_Stitching
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.
Implicit_Neural_Representation
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).
Lane_Detection
Lane Detection using classical approach and a deep learning based approach
manipulator_control_DDPG
Controlling a 7 DOF manipulator from the panda gym reacher environment using DDPG
Neural_Surfaces
Sphere Tracing. Optimizing a Neural SDF. VolSDF. Phong Relighting.
Point_Cloud_Analysis
Estimating Ground Surface Normals and Fitting Surfaces to Noisy LIDAR Point Cloud Data
PointCloud_Classification_and_Segmentation
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.
PyTorch3D_Rendering_Basics
Learning the basics of rendering with PyTorch3D, exploring 3D representations, and practicing constructing simple geometry.
Single_View_to_3D
Exploring the types of losses and decoder functions for regressing to voxels, point clouds, and mesh representations from single view RGB input.
Superpixels_and_SLIC
Basic implementation of SLIC algorithm for generating superpixels.
omkarchittar's Repositories
omkarchittar/PointCloud_Classification_and_Segmentation
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.
omkarchittar/Single_View_to_3D
Exploring the types of losses and decoder functions for regressing to voxels, point clouds, and mesh representations from single view RGB input.
omkarchittar/Point_Cloud_Analysis
Estimating Ground Surface Normals and Fitting Surfaces to Noisy LIDAR Point Cloud Data
omkarchittar/Neural_Surfaces
Sphere Tracing. Optimizing a Neural SDF. VolSDF. Phong Relighting.
omkarchittar/PyTorch3D_Rendering_Basics
Learning the basics of rendering with PyTorch3D, exploring 3D representations, and practicing constructing simple geometry.
omkarchittar/Superpixels_and_SLIC
Basic implementation of SLIC algorithm for generating superpixels.
omkarchittar/Image_Stitching
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.
omkarchittar/Lane_Detection
Lane Detection using classical approach and a deep learning based approach
omkarchittar/Semantic_Segmentation_and_Object_Detection
This repository showcases the implementation of both Semantic Segmentation Model and Object Detection Models for Self-Driving Cars.
omkarchittar/smarter-university-system
Smarter University System (SUS)
omkarchittar/Trajectory_Tracking
Analysis of the trajectory of a red ball thrown against a wall in a video using image processing techniques and standard least squares.
omkarchittar/Tsai_Camera_Calibration
Calibrating camera using Tsai camera calibration method
omkarchittar/Camera_Pose_Estimation
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.
omkarchittar/Face_Reconstruction
Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.
omkarchittar/blog
SvelteKit blog
omkarchittar/Control_of_Crane_System
Design and Simulation of LQR and LQG Controller for Crane System
omkarchittar/Dijkstra_Point_Robot
In this project, the Dijkstra's path planning algorithm was implemented on a point robot for helping it navigate through an obstacle filled space.
omkarchittar/Generative_Adversarial_Networks
Generative Adversarial Networks on MNIST and Human Faces Dataset
omkarchittar/K_Means_Clustering
Color based image segmentation
omkarchittar/LiDAR_SLAM
omkarchittar/MonteCarlo_Localization
Mapping based on Monte Carlo particle filter with lidar scan, accelerometer and gyroscope data.
omkarchittar/Neural_Radiance_Fields
Perform Differentiable Volume Rendering: Ray sampling from cameras, Point sampling along rays. Optimizing a basic implicit volume, Optimizing a Neural Radiance Field.
omkarchittar/omkarchittar
omkarchittar/omkarchittar.github.io
omkarchittar/Pose_Estimation_2D
This repository contains the Pytorch code for human pose estimation using the CAREN dataset.
omkarchittar/quizify
Using Google Gemini to generate quizzes from any sets of pdf files
omkarchittar/SentimentScope
Interpretation and classification of emotions (positive, negative and neutral) within text data using text analysis techniques.
omkarchittar/Stereo_Depth_Estimation
Implementing the concept of Stereo Vision. We are given 3 different datasets, each of them containing 2 images of the same scenario but taken from two different camera angles. By comparing the information about a scene from 2 vantage points, we can obtain the 3D information by examining the relative positions of objects.
omkarchittar/Structure_from_Motion
omkarchittar/Zhang_Camera_Calibration
Calibrating camera using Zhang's camera calibration method