In order to fulfill the basic functions of our service, the user hereby agrees to allow Xiaomi to collect, process and use personal information which shall include but not be limited to written threads, pictures, comments, replies in the Mi Community, and relevant data types listed in Xiaomi's Private Policy. By selecting "Agree", you agree to Xiaomi's Private Policy and Content Policy .
Agree

Tech

[News] Qualcomm future of AI photography

2019-07-16 09:44:33
362 14

Hello Mi Fan's!!!

In addition to computation photography, high-quality camera hardware, and image signal processors, cutting edge mobile photography is increasingly powered by machine learning algorithms — also known as artificial intelligence (AI). This photography technique promises to improve quality in the push towards DSLR-like quality while offering creative new ways to shoot and edit pictures and video.

The key to machine learning is the use of neural networks. This is a type of algorithm that is often likened to the human brain. This comparison is drawn from a neural network’s ability to be trained, through the use of data, to recognize patterns, allowing it to make highly accurate classifications for complex data types like audio and images.

When it comes to photography, the ability to observe, learn, generate, and classify has a wide range of applications. These applications can include features such as building on computational photography techniques to improving post-processing algorithms, real-time software bokeh with 4K video, or even completely swapping out the colors of the clothes you’re wearing.

How neural networks work?

Neural networks are a hugely complex topic, so we’re only going to cover the basics here. For more advanced reading, check out guides here and here.

Neural networks are made up of nodes, which is a signifier for where some computation is done. Each node combines an input with a weight which amplifies or attenuates the significance of that particular node. Several nodes often work in parallel, creating a layer of nodes that performs a larger task. This could be feature detection within an image, for example. Multiple nodes and layers can be summed together and passed on to other nodes and layers, forming a deeper network with more powerful capabilities.


The output from each node and layer is scaled as a probability function. By looking at lots of different features and attributes, a neural network can rate the input as a probability match against all of the expected potential outputs. This is how image detection algorithms decide whether a picture looks more like a cat or an orange, but you have to tell it what to look for first.

Neural networks aren’t programmed quite like traditional computer algorithms. Instead, they are trained on datasets, such as images, sound files, etc. The weights of each node are adjusted gradually over time via a feedback loop, based on how well the network did at matching the inputs to the correct outputs. This gradual “learning” of the rules takes considerable preparation, time, and computing power, but produces phenomenally accurate results.

Neural networks inside your smartphone

Neural networks can run on a variety of hardware components, including the CPU and GPU parts common inside a range of computing devices, including your smartphone. However, some neural networks can require more processing power than these hardware components can give, and dedicated hardware can provide the optimal processing needed.

Inside the Qualcomm® Snapdragon™ 855Mobile Platform, for instance, you’ll find the latest Qualcomm® Hexagon™ 690 Digital Signal Processor (DSP), boasting improved Vector processing units and a new Tensor Accelerator specifically for machine learning tasks. Other Snapdragon Mobile Platforms also feature the Hexagon DSP component, with varying capabilities. With that said, neural nets aren’t limited to just running on the DSP on Snapdragon and other mobile platforms. The type of processor used depends on the workload.


Qualcomm Snapdragon 855 Machine lernilea improvements compared to the previous generation

Qualcomm Technologies opens up its DSP and machine learning capabilities to third-party developers through its Qualcomm® Neural Processing SDK. This allows apps to run neural nets across any of the hardware cores inside a Snapdragon Mobile Platform. For example, Google Pixel smartphones tap into the Hexagon DSP and its own Visual Core to accelerate its impressive HDR+ photography feature. Qualcomm Technologies works with software vendors such as Arcsoft, Elevoc, Polar, Loom, Mobius, Morpho, and more, supporting features ranging from video bokeh to avatar creation using machine learning running on the DSP.


AI cloud shape the future of photography

Now we know how neural networks work, the important question is what could it do for us and our photographs?

Neural networks are used to improve a range of common photography algorithms. De-noise, for example, could be improved with training to offer superior image clean up tailored to the specific camera or type of shot. Likewise, for low light, a neural net could detect bright and dark parts of the image, allowing for light and color enhancements in specific parts of the scene.

More advanced use cases are increasingly common in smartphone photography. Super-resolution zooms use neural nets to combine multiple images into a single high-resolution shot for superior looking digital zoom. Neural nets could also be trained to accurately stitch multiple photo exposures together for enhanced HDR and night shots.

AI photography could include super-resolution zoom, real-time bokeh, and improved image quality.

Video could also benefit from the adoption of this technology. Real-time object detection is designed to allow apps to introduce software bokeh effects straight into video as you record. Similar techniques also support real-time object swapping and removal. This includes swapping out the background in a video, changing or removing colors, and even replacing items of clothing or superimposing digital avatars directly into your video.

The power of neural networking and AI photography ranges from quality enhancements to help close the gap on DSLR to powerful creativity tools that help make producing unique content a breeze. Either way, it’s a powerful technology that’s fundamental to future improvements heading to mobile photography.

Source

Rate

Number of participants 1 Experience +10 Pack Reason

View Rating Log

2019-07-16 09:44:33
Favorites7 RateRate
WOW, Great news, Thanks for sharing
2019-07-16 10:07:33

Grand Master Bunny

Seragios | from Redmi 5

#2

Great, Thanks for sharing
2019-07-16 11:06:46
Thanks for sharing
2019-07-16 11:18:11

Master Bunny

Ady026 | from Mi Note 3

#4

Thanks for information
2019-07-16 12:14:25

Beta Team-Global

jagdevkumhar | from Redmi 6 Pro

#5

thanks for sharing
2019-07-16 12:28:34
jagdev

Master Bunny

MeL Harris | from Redmi Note 5

#6

thanks for sharing
2019-07-16 12:45:41

Master Bunny

frost_dragneel | from Redmi Note 6 Pro

#7

thnks for sharing
2019-07-16 13:05:28

Pro Bunny

Татэй | from app

#8

Thanks for sharing.     
2019-07-16 14:08:57

Master Bunny

Erdinçer | from MI MAX 2

#9

Thanks for the good info
2019-07-16 17:13:56

Master Bunny

1630485853 | from Redmi Note 7

#10

Thanks for sharing
2019-07-16 17:33:04
please sign in to reply.
Sign In Sign Up

ᎮᏒᎥᏁፈᏋ

News Reporter

  • Followers

    229

  • Threads

    997

  • Replies

    2028

  • Points

    25170

Check-in 3 jours
Check-in 7 jours
Check-in 21 jours
Check-in 40 jours
Check-in 70 jours
Check-in 100 jours
10k
New Home
10k Mi Fans
Redmi Note 7
Cast Away
20K Mi Fans
30K Members
Mi Love U & I
Limited Edition Space Medal
Bunny Winner
20K Mi Fans
Mi 9 & Mi 9 SE
70K Fans
Android Q
2 años
Mother's Day
Día de las Madres
Best Mi
Happy Mother's Day
Android Q
50K Mi Fans
Mobile Photography Lover
X-MEN. Desata tu poder
25K
Favorite X-Men
Medalla X-Men: Bestia
Medalla X-Men: Cíclope
X-Men: Mística
Medalla X-Men: Magneto
70K Mi Fans
Challenger
40K Registered Users
Eid Mubarak
Eid ul-Fitr Mubarak
Brain Teaser
X-Men Favorite Medal
Perfil Personalizado
80K Mi Fans
200k Member
Tech Talent
Orgullo
100K Mi Fans
Selfie Day
50K Users
Mi 9T
Medalla Mi Community
MIUI Geek
Fortune 500
Fortune 500
Three's A Party
Happy July
Mi 9T
Global Fans
My Country My Pride
Redmi 7A
Fortune Global 500
FORTUNEGLOBAL500
Mi 9 SE
60K Registered Users
Like
Check in
Reply
Favorites
Post
FortuneGlobal500
Profile Medal
Eid Al-Adha Mubarak
9YearsWithMIUI
Fortune Global 500
MIUI 9th Birthday
Global Community
70K
У які ігри ви граєте найбільше?
Global Community
Mejor Contenido Agosto
Mi A3
80K Medal
Medalla Encuesta Mi Phone
80K
wallpaper votes
500
Redmi 7A
better together slogan
Global Community
device poll
better together with friends
games discuss
Puzzle Master
Mid-Autumn Festival

Read moreGet new
Copyright©2016-2019 Xiaomi.com, All Rights Reserved
Content Policy
Quick Reply To Top Return to the list