Aman Agarwal's repositories
nerf-pytorch
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
svox2
Plenoxels: Radiance Fields without Neural Networks
c-ray
c-ray is a small, simple path tracer written in C
torch-merf
An unofficial pytorch implementation of MeRF
3Dify
Constructing 3D models out of 2D images
CLEVR-Object-Centric
This repository generates multi-view observations for static/dynamic CLEVR scenes.
projection-conditioned-point-cloud-diffusion
Official code for "Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction"
loan-default
Creating a robust model that can help lenders and financial institutions make informed decisions on extending or denying credit
Diffusion-GAN
Official PyTorch implementation for paper: Diffusion-GAN: Training GANs with Diffusion
Image-colorization
An attempt to colorise black and white images via the use of Auto-encoders
torch-blitz
A Quick Torch Recap and Revision via paper implementations in Pyt
ModernCPP
Learning Modern CPP with OPENCV4 for Computer Vision and Image Processing
Diffusion-model-detector-simulation
Diffusion Models for Fast Detector Simulation
sneha1012.github.io
Personal Portfolio
Vision-transformer-for-E2E-CMS
Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment
bop_toolkit
A Python toolkit of the BOP benchmark for 6D object pose estimation.
Perception
Studying perception, methods of Augmented Reality and visual metrology
VideoTo3D
3D Reconstruction via Videos
detector
Mirror of https://github.com/facebookincubator/deltille
MultiView-3D-Reconstruction
Using traditional image processing techniques to construct 3D point cloud of objects. Incremental Structure from Motion (SfM) is used, a popular SfM algorithm for 3D reconstruction for reconstruction. The method is then evaluated using certain 3D reconstruction datasets.
ImageProcessing
Implementations of Image Processing principles taught in First Principles of Computer Vision
diffusion-point-cloud
:thought_balloon: Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)
VQA-Flask-App
A simple Flask app to generate answer given an image and a natural language question about the image. The app uses a deep learning model, trained with Tensorflow, behind the scenes.
TicTacToe
A TCP Client Server based Tic Tac Toe
3D-Vision
A Dive into world on 3D Vision/SLAM via Machine Learning
TEASER-plusplus
A fast and robust point cloud registration library
JavaScript-SRM
A repository of syllabus based JavaScript codes