Blog

Introduction

In this post, I’ll explore how I made a Lens that features an animated phoenix flying through an AR scene anchored to the ground. This is the finished Lens:

To get there, we will leverage the Refinement Pack and Particles template from Lens Studio, as well as a 3D phoenix asset from Sketchfab.

Specifically, this post will cover:

Moving an object along a 3D path through the scene using a Prefab from the Refinement Pack Applying a texture to a 3D model of a phoenix downloaded from Sketchfab Working with particle emitters to add a stationary column of smoke, embers throughout the scene, and a bokeh effect that follows the phoenix

Let’s dive in!

Continue reading “Creating an Animated 3D Phoenix Lens in Lens Studio”

Before we begin, let’s get started by answering the following question:

What is a type?

The answer to this question is fairly simple—a type is a collection of related data that encapsulates certain concepts and principles. A type can be abstract or concrete, it defines a set of valid operations that we can perform on it, and finally, a type clearly demarcates the internal and external.

Continue reading “Equality, Identity, and Hashing with Swift Types”

In this series, we’re learning about SwiftUI by making a profile page. And so far, we’ve accomplished a very simple—yet stylish—profile for ourselves in just a few paragraphs of code!

Continue reading “SwiftUI: Making Views More Dynamic and Reusable”

Gesture recognition helps us to know the meaning of human body movement, including the movement of hands, head, arms, face, or body. Today’s world is observing huge advances in visualization displays and this includes object trackers in AR applications.

The main purpose of this article is to explore gesture recognition in Facebook’s Spark AR Studio for an efficient human-computer interaction. It presents a method for tracking hand gestures and recognizing hand gestures by extracting unique invariant features from gestures.

Continue reading “Add a Hand Tracker and 3D Object in Facebook’s Spark AR Studio”

Over the past 3 years, our incredible community of contributing writers, developers, and creators have helped us explore the foundations of machine learning, mobile development, and where these two areas of tech intersect.

To date, we’ve published work from more than 150 individual contributors from over a dozen countries around the world — those voices have helped build an incredible library of foundational blog posts and articles that offer both beginners and seasoned developers educational resources, industry insights, research reviews, and much more.

Continue reading “Heartbeat Contributor Program: Announcing new content topics”

Recently, I wrote two articles about training object detection Core ML models for iOS devices using TensorFlow and Turi Create frameworks.

To train those models, I used a tool I’d built called MakeML. It allows you to easily create a dataset, label it, and start training. There’s no need to write code with MakeML, so every iOS developer can train an object detection machine learning model in a couple of hours. On paper, at least…

Continue reading “MakeML’s Automated Video Annotation Tool for Object Detection on iOS”

Generally, in machine learning problems, we often encounter too many variables and features in a given dataset on which the machine learning algorithm is trained.

The higher the number of features in a dataset, the harder it gets to visualize and to interpret the results of model training and the model’s performance. Moreover, when dealing with such a massive dataset in terms of features, the computational costs should be considered.

Continue reading “Demystifying Principal Component Analysis: Handling the Curse of Dimensionality”