Pinned Repositories
3DPointCloud-IterativeClosestPoint
Iterative Closest Point Algorithm is one of the best algorithm to register 3D Point Clouds. This code is about registration/alignment of point cloud data collected for an object from different camera positions.
6DPoseEstimationCNN
Multi Stage Convolutional Neural Network Based 6D Pose Estimation. In this repo, I provide code for my [IROS 2018 ]paper, "Detect Globally, Label Locally: Learning Accurate 6-DOF Object Pose Estimation by Joint Segmentation and Coordinate Regression". Paper proposes a deep architecture with an instance-level object segmentation network that exploits global image information for object/background segmentation and a pixel-level classification network for coordinate regression based on local features. We evaluate our approach on the standard ground-truth 6-DOF pose estimation benchmarks and show that our joint approach to accurate object segmentation and coordinate regression results in the state-of-the-art performance on both RGB and RGB-D 6-DOF pose estimation.
apurvmmmec.github.io
Personal Blog
AutomaticVideoSummarization
This code demonstrates Automatic Video Summarization Technique. This can be useful for surveillance applications or motion based summarisation of videos.
DroidconVirtualReality
I wrote this short tutorial as part of a hand-on Virtual Reality Workshop in DroidCon 2015 Developer Conference in India where I was a speaker for an audience of around 200 developers from across the country. https://www.slideshare.net/ApurvNigam1/virtual-reality-application-development-on-android-using-google-cardboard
MeshSmoothing
This code is to demonstrate the powerful use of Laplacian Beltrami Operator for performing iterative smoothing of a 3D mesh. Both the Implicit and Explicit Smoothing have been demonstrated. Implicit Smoothing is however numerically more stable as compared to explicit smoothing and more practical to use.
Non-LocalMeans-ImageDenoising
This repository has code for Image Denoising using Non-Local Means and Integral Images. Non-Local Means takes into account the global information of image and computational efficiency of Integral Images.
OpenGL-Rendering-Rasterization-Techniques
This repo shows the webGL code for different types of rendering techniques right from the most basic one which is Rasterization, to Ray Tracing to the most realistic one called Global Illumination/Path Tracing. The rendered scenes are the most basic ones.
Poisson-Image-Inpainting
In this repo, I provide code for seamlessly blending patches of image from source image into destination image using Poisson equations. I also demonstrate techniques to achieve nice effects like changing color of selected regions of image, seamless tiling in images, inserting or removing local illumination effects and texture flattening.
RoboticSLAMVisualOdometry
This code shown the use of Bundle Adjustment to construct the 3D map of the environment as well as calculate the camera poses from each frame.
apurvmmmec's Repositories
apurvmmmec/3DPointCloud-IterativeClosestPoint
Iterative Closest Point Algorithm is one of the best algorithm to register 3D Point Clouds. This code is about registration/alignment of point cloud data collected for an object from different camera positions.
apurvmmmec/6DPoseEstimationCNN
Multi Stage Convolutional Neural Network Based 6D Pose Estimation. In this repo, I provide code for my [IROS 2018 ]paper, "Detect Globally, Label Locally: Learning Accurate 6-DOF Object Pose Estimation by Joint Segmentation and Coordinate Regression". Paper proposes a deep architecture with an instance-level object segmentation network that exploits global image information for object/background segmentation and a pixel-level classification network for coordinate regression based on local features. We evaluate our approach on the standard ground-truth 6-DOF pose estimation benchmarks and show that our joint approach to accurate object segmentation and coordinate regression results in the state-of-the-art performance on both RGB and RGB-D 6-DOF pose estimation.
apurvmmmec/RoboticSLAMVisualOdometry
This code shown the use of Bundle Adjustment to construct the 3D map of the environment as well as calculate the camera poses from each frame.
apurvmmmec/Non-LocalMeans-ImageDenoising
This repository has code for Image Denoising using Non-Local Means and Integral Images. Non-Local Means takes into account the global information of image and computational efficiency of Integral Images.
apurvmmmec/OpenGL-Rendering-Rasterization-Techniques
This repo shows the webGL code for different types of rendering techniques right from the most basic one which is Rasterization, to Ray Tracing to the most realistic one called Global Illumination/Path Tracing. The rendered scenes are the most basic ones.
apurvmmmec/Poisson-Image-Inpainting
In this repo, I provide code for seamlessly blending patches of image from source image into destination image using Poisson equations. I also demonstrate techniques to achieve nice effects like changing color of selected regions of image, seamless tiling in images, inserting or removing local illumination effects and texture flattening.
apurvmmmec/MeshSmoothing
This code is to demonstrate the powerful use of Laplacian Beltrami Operator for performing iterative smoothing of a 3D mesh. Both the Implicit and Explicit Smoothing have been demonstrated. Implicit Smoothing is however numerically more stable as compared to explicit smoothing and more practical to use.
apurvmmmec/apurvmmmec.github.io
Personal Blog
apurvmmmec/AutomaticVideoSummarization
This code demonstrates Automatic Video Summarization Technique. This can be useful for surveillance applications or motion based summarisation of videos.
apurvmmmec/DroidconVirtualReality
I wrote this short tutorial as part of a hand-on Virtual Reality Workshop in DroidCon 2015 Developer Conference in India where I was a speaker for an audience of around 200 developers from across the country. https://www.slideshare.net/ApurvNigam1/virtual-reality-application-development-on-android-using-google-cardboard
apurvmmmec/SegmentationFullyConvolutionalNetwork
This repo contains code to use Deep Learning to segment objects from background. I have trained Fully Convolutional Network[1] to segment objects in Hinterstoiser Dataset from a cluttered background.
apurvmmmec/sortingApp
Simple Android Application to demonstrate simple sorting algorithms
apurvmmmec/tesseract
Tesseract Open Source OCR Engine (main repository)