Author: datahacker.rs

#027 R-CNN, Fast R-CNN, and Faster R-CNN explained with a demonstration in PyTorch

Highlights: Object detection is one of the most important tasks in Computer Vision. In this post, we will give an overview of one of the most influential families of object detection algorithms: R-CNN, Fast R-CNN, and Faster R-CNN. We will highlight the main novelties and improvements for each of them.  Finally, we will focus on the Faster R-CNN and explore the code and how it can be used in PyTorch.  Tutorial Overview: 1. Introduction to…
Read more

#016 3D Face Modeling – Linear camera model

Highlight: In this post, we are going to talk about what calibration is and how it is performed. Calibration represents the process of going from one coordinate system to another, for example going from meters to pixels. We will explain how an image is formed, in more detail, how we go from the 3D scene in the real world to the 2D image plane in the camera. In this post, we are going to review…
Read more

#015 3D Face Modeling – The geometric image formation

Highlight: In this post, we are going to talk about the geometric image formation process and some basic camera models. We will explain in detail how 3D points/lines are projected in 2D planes. How it all started. Inside an entirely dark room that had only one little pinhole in the door, the outside scenes and objects were projected upside down onto the dark wall. This was due to the illumination of the light that was…
Read more

#013 3D Face Modeling – Creating a 3D model of a cube from one image

Highlights: Hello, and welcome. In this post, we’re going to talk about how we can create a 3D model of a cube with only one image as input. The way we are going to achieve this is the same as we explained previously for the 3D face model. So let us begin! 1. Creating 3D cubes The first step we need to do is to create different 3D cubes to replicate a database of 3D…
Read more

#014 3D Face Modeling – Understanding primitives and transformations for image formation (Version B)

Highlight: Hi and welcome to our new post! In this post, we will continue our journey of understanding how fundamental computer vision techniques work. We first need to understand how images are formed, and how to go from a 3D scene to a 2D image. By understanding this we can develop models that mathematically formalize this process. So, let us start. Understanding what are primitives They represent the basic building blocks that are used to…
Read more