Technical Specification
This page provides technical metrics of Face AR SDK feature performance. The values below are for your reference only. We received them on fixed conditions. However, many factors may influence the actual technology performance, e.g. the state of device, other apps running, wi-fi enabled, room temperature, etc. We encourage you to test each feature within your environment.
Please visit SDK Features and SDK Features for Unity for the information regarding features support on different platforms.
- FPS — Frames per second of the face detection algorithm on a given device.
- Angles — Maximum angle on which the technology was able to work during the measurement.
- Distance — Maximum distance on which the technology was able to work during the measurement.
- Real-time (online) — Technology performance in real-time.
- Photo (offline) — The processing time needed to take a photo or process it from the gallery.
SDK Features
Face Detection
Android
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| FPS | 20 | 30 |
| Angles, degree | 70 | 70 |
| Distance, cm | 160 | 160 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| FPS | 30 | 30 |
| Angles, degree | 70 | 70 |
| Distance, cm | 180 | 180 |
Single-face Tracking
Android
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| FPS | 30 | 30 |
| Angles, degree | 70 | 70 |
| Distance, cm | 180 | 200 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| FPS | 30 | 30 |
| Angles, degree | 70 | 70 |
| Distance, cm | 180 | 200 |
Multi-face Tracking
Android
| Android Mid Redmi Note 9S | Android Top OnePlus8 | |
|---|---|---|
| Faces Number | 3 | 3 |
| 2 Faces, FPS | 20 | 20 |
| 3 Faces, FPS | 20 | 20 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Faces Number | 3 | 3 |
| 2 Faces, FPS | 30 | 30 |
| 3 Faces, FPS | 30 | 30 |
Faces Number* — Maximum number of faces which SDK can track with acceptable quality and performance on most mobile devices. The actual number allowed for multi-face tracking is not limited by the technology but only by the physical ability of the device and proportions of the screen.
Effect performance
Banuba SDK allows for a variety of Face AR effects. Some of them require only face tracking and can be represented as a single 3D mask with textures and materials. Other effects are implemented with separately trained neural networks.
Below, you may find information on the real-time performance of Face AR effects which require only face tracking, i.e. face filters, avatars with action units, beautification, and makeup filter (without lipstick).
Android
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| FPS | 30 | 30 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| FPS | 30 | 30 |
Beautification
Beautification filter
Basic face beautification filter includes skin smoothing, morphing, teeth whitening, eyes flare and LUT. It requires only face tracking, so please, refer to the Effects performance section. Other features given below are based on neural networks, and their performance differs.
Acne removal (manual)
iOS, neural network, photo processing (offline only)
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Photo, sec | < 1 | 1 |
Android, neural network, photo processing (offline only)
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| Photo, sec | < 2 | < 1 |
Acne removal (auto)
iOS, neural network, photo processing (offline only)
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Photo, sec | < 1 | 1 |
Android, neural network, photo processing (offline only)
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| Photo, sec | < 2 | < 1 |
Eye bag removal
iOS only, neural network, photo processing (offline only)
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Photo, sec | < 2 | < 1 |
Makeup
The Makeup filter allows for a realistic try on of foundation, eyeshadow, eyeliner, highlighter, contour, and blusher. It requires only face tracking, so please, refer to the Effects performance section. The lipstick try on requires lips segmentation neural network with a separate algorithm for Lips Shine effect.
Lips coloring
Android
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| Real-time, FPS | 23 | 30 |
| Photo, sec | < 2 | 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time, FPS | 30 | 30 |
| Photo, sec | < 1 | < 1 |
Web
| Real-time, FPS | |
|---|---|
| Chrome | 26 |
| Safari | 16 |
Lips Shine (Glossy lipstick)
Android
| Android Mid Redmi Note 9S | Android Top OnePlus8 | |
|---|---|---|
| Real-time, FPS | 18 | 30 |
| Photo, sec | 2 | 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time, FPS | 30 | 30 |
| Photo, sec | < 2 | < 1 |
Web
| Real-time, FPS | |
|---|---|
| Chrome | 28 |
| Safari | 17 |
Background separation
Android
| Android Mid Samsung Galaxy S7 | Android Top Pixel 3 XL | |
|---|---|---|
| Real-time,FPS | 20 | 30 |
| Photo, sec | < 3 | < 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time, FPS | 30 | 30 |
| Photo, sec | < 1 | < 1 |
Distance
| Device | Distance, cm |
|---|---|
| iPhone 7 | Portrait 230 cm, Landscape 220 cm |
| iPhone 12 | Portrait 230 cm, Landscape 250 cm |
| OnePlus8 | Portrait 330 cm, Landscape 320 cm |
| MacBook Pro (15", 2018) | 270 cm |
Image formats support
Currently, the following images formats are supported as background texture:
.jpeg.jpg.png.ktx.gif
Video formats support
Used as part of animated background.
| Video format | MacOS | iOS | Android* | Windows |
|---|---|---|---|---|
| .mp4 | ✅ | ✅ | ✅ | ✅ |
| .avi | ✅ | ❌ | ❌ | ✅ |
| .flv | ✅ | ❌ | ❌ | ✅ |
| .mkv | ✅ | ❌ | ✅ | ✅ |
| .mov | ✅ | ✅ | ❌ | ✅ |
| .mts | ✅ | ❌ | ❌ | ✅ |
| .webm | ✅ | ❌ | ✅ | ✅ |
| .wmv | ✅ | ❌ | ❌ | ✅ |
* See more information about supported video formats on Android in the official Android developers guide — https://developer.android.com/guide/topics/media/media-formats#video-codecs.
Hair segmentation
Hair Recoloring
Android
| Android Mid Redmi Note 9S | Android Top OnePlus8 | |
|---|---|---|
| Real-time,FPS | 20 | 30 |
| Photo, sec | < 1 | < 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time,FPS | 30 | 30 |
| Photo, sec | < 1 | < 1 |
Hair Strands Recoloring
iOS online
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| FPS | 20 | 30 |
iOS offline
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Photo, sec | < 2 | < 1 |
Android online
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| FPS | 20 | 20 |
Android offline
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Photo, sec | < 2 | < 2 |
Skin segmentation
Android
| Android Mid Redmi Note 9S | Android Top OnePlus 8 | |
|---|---|---|
| Real-time,FPS | 30 | 30 |
| Photo, sec | < 1 | 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time,FPS | 30 | 30 |
| Photo, sec | < 1 | 1 |
Eyes recoloring
Android
| Android Mid Redmi Note 9S | Android Top Pixel 3 XL | |
|---|---|---|
| Real-time,FPS | 20 | 30 |
| Photo, sec | < 2 | < 1 |
iOS
| iOS Mid iPhone 7 | iOS Top iPhone 11 | |
|---|---|---|
| Real-time,FPS | 30 | 30 |
| Photo, sec | < 1 | < 1 |
Hand gestures
Basic information
- Supported gestures:
- Palm ✋
- Victory✌️
- Rock 🤘
- Like 👍
- Ok 👌
- Maximum distance — 1.1m
iOS
| Device | Realtime FPS* |
|---|---|
| iPhone 11 | 103 |
| iPhone 7 | 77 |
* Means technology FPS. In real usage, FPS is usually limited with the render value and locked by 30 or 60 FPS.
Android
| Device | Realtime FPS* |
|---|---|
| top-end OnePlus | 68 |
| middle-end Xiaomi | 51 |
* Means technology FPS. In real usage, FPS is usually limited with the render value and locked by 30 or 60 FPS.
Full Body segmentation
iOS
| iPhone 7 | iPhone 11 | |
|---|---|---|
| Real-time, FPS* | 30 | 30 |
| Photo, sec | < 1 | < 1 |
| Activation time, sec | ~2 | ~1 |
| Memory usage, mb | 148 | 124 |
* Means technology FPS. In real usage, FPS is usually limited with the render value and locked by 30 or 60 FPS.