Best AR SDK for development for iOS and Android in 2018
Have you ever dreamed of making your own Augmented Reality app? But you don’t know how to start? So, let’s see our massive investigation of Augmented reality SDK. This article will help you increase your knowledge on Unity 3D and augmented reality development. This guide could be equally useful for beginners or skilled software developers. Using the following augmented reality frameworks and source codes let’s start your AR app right now!
Supported platforms: Android, iOS, Windows for tablets, smart glasses (Epson Moverio, Vuzix M100, ODG R-7).
In July 2018 Wikitude released the latest version of powerful SLAM solution for augmented reality apps: Wikitude SDK 8. Working with is seamless for any skilled developer – download the SDK and a sample app, study the documentation and start creating!
Wikitude is constantly improving their product, adding more and more functional features in each release. So, in addition to such paramount features of SDK 7 as image recognition, object recognition, 3D markerless tracking, ARKit and ARCore support, this new version offers even more:
- Scene recognition (augment large objects for outdoor gaming, construction, etc.),
- New extended recording and tracking of objects (scan and see augmented objects beyond markers),
- Instant targets (save and share instant augmentations),
- Unity live preview (AR-view feature into Unity editor to test the SDK features),
- Windows support.
With over 1 billion app installs and as one of the fastest-growing AR ecosystems, Wikitude recently added a free Startup Product to its offering.
Wikitude offers the opportunity to try the free trial version with watermark and the full power of the platform. The cost of this cross-platform Augmented Reality SDK starts at 1990 Euros. Also worth noting, Wikitude is more beneficial when developing markerless AR apps for iOS/Android, compared to ARKit and ARCore (and both libraries have been added to Wikitude recently).
Besides, Wikitude SDK isn’t limited only with SLAM – you can expand your app by image recognition to enhance print promo materials, or by geo-AR to show directions to closest stores/offices, etc.
|2D Image Recognition||2D Image Recognition||2D Image Recognition||2D Image Recognition||2D Image Recognition|
|3D Image Recognition||–||3D Image Recognition||3D Image Recognition||3D Image Recognition|
|–||–||–||Cloud Recognition||Cloud Recognition|
|Watermark||No watermark||No watermark||No watermark||No watermark|
|Free||Starting at €1990 per app||Starting at €2490 per app||€4490 per app||Call|
Intoruding Augmented Reality development for iOS, one of the biggest mobile platforms of today. ARKit is an SDK for software developers to create augmented reality apps and games for iPhones and iPads.
Supported platforms: iOS 11/12.
AR apps that one builds with ARKit require iOS 11 or 12. Apple’s SDK utilizes iPhone/iPad hardware, motion sensors, camera to enable Augmented Reality applications. So, basically, iPhone 6/6 Plus/7/7 Plus/8/8 Plus/X and iPad Pro models support th, and this means literally millions of mobile devices.
ARKit supports 2-dimensional image detection (trigger AR with posters, signs, images), and even 2D image tracking, meaning the ability to embed objects into AR experiences. SDK allows developing apps that would recognize spaces and 3D objects, as well as place virtual objects on surfaces. One great example is Ikea Place app, where one can place virtual furniture items in his/her own real space.
In June 2018 Apple launched a new updated version – ARKit 2, coming out alon with and for iOS 12. A huge leap forward in it is multiplayer games to be able to share the AR experience with others. This SDK enables making games that can be played, for instance, between two iPads by two different people.
Google’s response to ARKit, ARCore is a developer platform for Augmented Reality design and deployment. With this SDK users’ phones are able to sense the external environment. What’s stunning about this AR SDK is that is supports both Android and iOS devices. Kudos to Google.
Supported platforms: Android 7.0 and higher, iOS 11 or higher.
ARCore comes with 3 core (no pun intended) capabilities to merge virtual and real worlds:
- Motion tracking – to track phone’s position relative to the surroundings.
- Environmental understanding – to detect the size/location of surfaces, from horizontal and vertical, to even angled surfaces.
- Light estimation – to estimate the real-life lighting conditions.
In essence, ARCore is based around 2 elements – real-time position tracking and integration of virtual and real objects. It lets you place objects, texts, etc. withing physical surroundings, and other people then can discover it with Android or iOS phones. To name few examples of its capabilities, we may enlist Just A Line app, ARuler app, Ikea Place.
Supported platforms: Android, iOS, UWP and Unity Editor.
Vuforia is one of the most popular platforms to help you work with augmented reality development. It implements the following functionalities: recognition of the different types of visual objects (a box, cylinder, plane), text and environments recognition, VuMark (a combination of picture and QR-code).
Also, using Vuforia Object Scanner, you can scan and create object targets. The recognition process can be implemented using the database (local or cloud storage). Unity plugin is simple to integrate and very powerful.
All plugins and functionalities of the platform are free to use but include the Vuforia watermarks. The limitations just relate to the number of VuMark and the number of Cloud recognition. Paid plan without watermarks and with a certain number of recos costs 99$ per month.
Since this article has been initially written, Vuforia has released new advanced editions – Vuforia 7 (December 2017) and 7.1 (March 2018). Rolling out the biggest release, Vuforia presented new capabilities for AR content:
- Vuforia Model Targets – introducing object recognition by shape, contrary to visual print media designs. This will help track images, scanned objects, special marks (encoded), text and surfaces.
- Vuforia Ground Plane – a feature for Unity engine that allows to place the augmented content on ground or surfaces. It helps to create high-quality visual apps and designs.
- Vuforia Fusion – a feature aimed at solving the fragmentation and enabling cameras, sensors, as well as external frameworks, e.g. ARKit.
- Vuforia 7.1 Update – a whole bunch of improvements on v.7 release, including automatic initialization on scenes with Vuforia components, removal of Google Tango support, option to clone objects, and more. In Vuforia 7.2 it is expected to expand to supporting ARCore, HoloLens and Universal Windows Platform devices.
|1,000 Targets||–||100,000 Targets||>100,000 Targets|
|Free||$499 / one-time per app||$99 / mo.||Call|
Supported platforms: Android, iOS, Windows, Mac OS.
Maxst offers two different tools for image and environments recognition. The generation of a database is online via Tracking Manager. To scan 3D objects are used applications for Android and IOS. In Unity Editor Maxst only works with the 32-bit version.
The free version differs from paid only by a watermark. PRO version cost 999$. The library is very easy to use and in integration. The official website has full and easy to understand documentation.
Pricing tiers for Maxst 3D:
|10 Targets||500 Targets||2000 Targets||Unlimited||Unlimited|
|1 Application license||Unlimited Application licenses||Unlimited Application licenses||Unlimited Application licenses||Unlimited Application licenses|
|Watermark||No Watermark||No Watermark||No Watermark||No Watermark|
|Free||$50 / mo.||$150 / mo.||$400 / mo.||$6500 single-user license|
A great tool from the US-based company of engineers, 3D designers and animators with 20 years of market presence, who have previously worked on Candy Crush, Hailo app, NASA and the Russian Space Agency. Along with special DeepAR Studio for content editing, they present DeepAR SDK.
It comes with 4 effect types: rigid objects, deformable masks, morph masks and post processing effects. This implies that developers can utilize this AR SDK for high quality face lenses, similar to ones on Snapchat and Facebook, as well as various masks and effects for mobile devices and desktop applications.
This Augmented Reality kit is capable of detecting faces and facial features in real time, based on patented data models and machine learning techniques. It is fast and recognizes about 70 facial points at 60 frames per second. In addition, DeepAR’s engine executes precise image rendering which is optimized for mobile and web apps, even for Android phones of lower specification.
Supported platforms: PC, Android, iOS, Windows, WebGL.
EasyAR is a free and easy to use alternative to Vuforia.
Supported platforms: Android, iOS, UWP, Windows, Mac and Unity Editor.
The latest version of EasyAR (1.3.1) supports the image recognition only. Version 2.0 will include the following features:
- 3D Object Recognition
- Environment perception
- Cloud Recognition
- Smart Glass Solution
- App Cloud Packaging
The library is completely free. To start your work with EasyAR, you only need to register the account and to generate the plugin’s key of your Bundle ID. EasyAR is quite easy to integrate. Documentation and examples are intuitively understandable.
Supported platforms: Android, iOS, Linux, Windows, Mac OS and Smart Glasses.
ARtoolKIt is an open source tracking library for augmented reality. ARtoolKit implements the following functionalities:
- Single-camera or stereo-camera camera position/orientation tracking.
- Tracking of simple black squares
- Tracking of planar images
- Camera calibration and optical stereo calibration
- Plugins for Unity and OpenSceneGraph
- Optical head-mounted display support
- Free and open source software
- Fast enough for real time AR applications
Variety of functions makes it difficult to integrate the library and takes more time to explore all options and settings.
Pricing: Free, open source.
Let's Build Your AR App
I agree to share this request with 10 development companies and get more offers
Xzimg from Hong Kong provides several specific AR SDK products, for real-time face tracking and creating AR-based apps, in particular. Such apps are good for desktop apps, mobile apps and web browsers via a Unity plugin.
Supported platforms: Android, iOS, Windows.
Xzimg incorporates three main products within its SDK:
- Augmented Vision – for computer vision functionality, marker recognition and tracking, that developers may deploy on smartphones and Windows platforms.
- Augmented Face – for human face recognition in videos, comes as a special Unity plugin.
- Magic Face – for non-rigid face tracking, refactoring from Augmented Face and enhancing with other features, like face replacement, face detection/tracking.
Pricing: Free trial version for non-commercial use / 2200 Euro for unlimited amount of apps.
SDK Feature Comparison Table
|Maximum distance capture (m)||2.4 / 5||1.5 / 5||1.0 / 3||1.2 / 3.7||0.5 / 0.9||0.7 / 5||0.9 / 2.7||3 / 3||0.5 / 1|
|Recognition stability of immovable marker||6||9||9||10||7||8||7||8||4|
|Recognition stability of movable marker||6||7||6||6||2||7||3||6||3|
|Minimum angle recognition||10||30||50||30||50||35||35||10||45|
|Minimum visibility for recognition overlapped marker||100%||50%||75%||20%||50%||10%||10%||100%||25%|
We have mentioned best tools for augmented reality development. Have we missed out some other decent SDKs? Let us know in comments.
Let's Build Your AR App
I agree to share this request with 10 development companies and get more offers