sobota 30. června 2018

How AI Helps Photographers Get More Creative

How AI Helps Photographers Get More Creative
Machine learning reveals a future that gives photographers more time for creativity
Na následující webové adrese najdete velmi přínosný článek, prezentující názory několika významných fotografů na otázky uplatnění AI ve fotografii. Dozvíte se prognózu jak se bude vyvíjet vztah fotografa a AI, jak můžeme chápat pojem "intelligent/creative assistent", jaká bude jeho role v podpoře rozvoje kreativity fotografa. Je to můj osobní názor, ale myslím, že text článku vnáší světlo do celé řady otázek spojených s AI ve fotografii, u kterých dochází často k mylným závěrům, vyplývajícím z nekomplexních přístupů.

Adresa plného znění článku je následující:

https://theblog.adobe.com/how-ai-helps-photographers-get-more-creative/
By Adobe Communications Team - POSTED ON 04-16-2018

Dovolím si citovat vybrané myšlenky. Upozorňuji, že z důvodu stručnosti nebudu uvádět autory a zdůvodnění. To vše se dozvíte v článku. 
- "Now that artificial intelligence (AI) is more deeply woven into photo editing and cataloging apps, the relationship between human and machine is taking a dramatic shift — a prospect that is thrilling some photographers, while intimidating others.
- “AI is not a substitute for creativity.” - When advancements in technology can enable a creative person to think less about the technology or the technical aspects of the profession and more about the content and message behind the photograph, the potential for elevating the visual literacy of an entire society is possible — and that’s exciting.”
- "Photo editing tools will transform from mere “apps” into a photographer’s virtual assistantremoving menial, creativity-killing tasks, helping photographers more clearly translate their visions to reality, and increasing their creative output.
- “As we continue to develop machine learning, we will also be able to help rank your photos based on aesthetics or composition, which does away with duplicate images,” she says.
“We’re not looking at machine learning as a way to replace our creativity, Humans are still the most creative entity in the human and machine relationship.”
- "Voice command capabilities could soon allow photographers to tell their software what basic tasks to complete — everything from cropping to adjusting lighting to more complex things like masking photos — allowing photographers to focus on the design that lets their creativity shine."
- “If the designers are designing, the creative assistant will analyze their document, their design, and will give them more intelligent suggestions — based on the colors they’re using, maybe even the font they’re using, maybe the title."
- "The result is a win for all photographers, regardless of their depth of expertise. It helps creative professionals achieve their vision more quickly and spend more time on the things that they actually like to do. But it also happens to make it easier for a beginner to be successful too.”
- “Stop worrying about AI. New technologies are coming out everyday, and it’s important to learn and adapt to them.”
“I find that the best way for me to find that middle ground is to have concept hold precedent over technology and the tools that I use to create. It’s the process of finding something beautiful, because if that beauty has started at a place of purity or a good concept, then the method of how you got there — whether it’s using AI technology or not — doesn’t really matter.”

pátek 29. června 2018

Luminar - Accent AI filter - Lutify LUTs

Luminar - Accent AI filter - Lutify LUTs
Otevřel jsem si LUMINAR 2018.
Načetl jsem obrázek večerní oblohy při západu slunce.
Použil jsem Accent AI filter
Zvolil jsem stažení nových LUTs.
Na serveru Lutify jsem stáhl sadu 3D Standard LUTs.
Rozbalil jsem ZIp soubor a načetl jsem zvolenou LUT.
Nastavení jsem uložil jako custom preset.
Exportoval jsem výsledný obrázek.
Načetl jsem jiný obrázek oblačné večerní oblohy.
Aplikoval jsem uložený Custom Preset.
Exportoval jsem zpracovaný druhý obrázek.
Tento proces jsem zaznamenal do sady slajdů.
Slideshow si můžete prohlédnout na adrese:
www.akamonitor.cz/sw/ai-filter
Pěkný článek pojednávající o možnostech aplikace Assent AI-filtru, najdete na adrese:
https://digital-photography-school.com/quickly-process-holiday-photos-luminar-accent-ai-filter/


3D Face Reconstruction from a Single Image

3D Face Reconstruction from a Single Image
3D obrázek vytvoříte z jediné fotografie na adrese

http://cvl-demos.cs.nott.ac.uk/vrn/view.php?name=a0092509903e41ba098112ff5e3d4967
Drag the 3D model around with your mouse
If it is blank, it may be an issue with WebGL or browser. Sometimes this happens with Chromium, but not Google Chrome, as far as I know.

úterý 26. června 2018

EVERYPIXEL - HODNOCENÍ OBRÁZKU

Ask neural network if your photo is good or not.Beta verzi tohoto AI nástroje najdete na adrese:https://www.everypixel.com/aesthetics
Webová služba je uvedena pouze stručným textem:"Ask neural network if your photo is good or not.
We trained  to see the beauty of stock photos in the same way as you do. Today our artificial intelligence algorithm is in the beta stage. Check how it works
TRY OUR SAMPLE".
Uvádím ukázku webové stránky s příkladem.
Najdete ji na adrese:
https://www.dropbox.com/s/skm9u11yxlm3exq/awesome1.jpg?dl=0

sobota 23. června 2018

AI and Skylum LUMINAR

What is the advancement of artificial intelligence for images and photography?
Hledal jsem na webu zdroje na téma "AI and photography" a našel jsem zajímavý článek Alexe Tsepka, CEO v Skylum Software, z 1. května 2018. 
Celý text najdete na adrese:
https://www.quora.com/What-is-the-advancement-of-artificial-intelligence-for-images-and-photography
V článku mne zaujaly informace o dvou produtech firmy Skylum software Photolemur a Luminar, které využívají umělou inteligenci ke zpracování fotografií. O programu Photolemur píšu na jiném místě v tomto weblogu. 
Tento krátký text s ukázkou, chci věnovat druhému produktu - Luminaru a jeho schopnosti upravit snímek pomocí jediného posuvníku ( jak o tom píše A. Tsepka ).
Cituji výňatek z článku:
"At Skylum, we’ve recently released a product called Photolemur. What it does is use artificial intelligence to edit photos to realize their best possible version without manual control. 
Using machine learning, the technology considers photos and lightens or darkens them depending on what the photo needs—all without the need of manual editing.
Control color and light with one slider. Another product we’ve launched is called Luminar, which allows photographers to use just one multifaceted slider to enhance their photos. We built this after hearing feedback from landscape photographers all over the world that having to use multiple sliders to edit their photos was too time consuming. Typically, photographers use dozens of sliders to improve a photo. They use sliders to highlight, or shadow, or create contrasts. With Luminar, however, photographers need just one slider. As you move it across a photo, the software decides how to tweak things like saturation, luminosity, and contrast. Again, it does this automatically. This sort of slider will soon be a norm."
Screenshot, pořízený v Luminaru, zobrazíte kliknutím na TÉTO adrese.
( https://www.dropbox.com/s/vreavzb06vb97q8/LUMINAR1.jpg?dl=0 )
A nakonec uvádím závěrečnou část článku, vyjadřující optimistický pohled na úlohu AI ve fotografii:
"No, what AI is doing instead is expanding photography’s reach, making it easier for more people to engage in this craft at an entry level––and capture great photos in the process. It enables amateur photographers––a bucket most of us fall into––to take beautiful pictures without having to learn words like saturation, luminosity, or contrast.
Everyone deserves the chance to immortalize important moments in their glimpses of beauty— things they want to remember. Soon, AI will allow all of us to more easily do exactly that."

čtvrtek 21. června 2018

AI Is Already Changing The Way We Think About Photography


AI Is Already Changing The Way We Think About Photography
Autor: Evgeny Tchebotarev ( Evgeny Tchebotarev founded 500px (acquired by VCG), backed by A16Z . He is VP Business Development Asia at Skylum and Director of Startup Grind Taipei. He is based in Taipei, Taiwan.)
Plné znění článku je na adrese:
https://www.forbes.com/sites/evgenytchebotarev/2018/05/30/ai-is-already-changing-the-way-we-think-about-photography/#7702d7cfbb6a
Cituji úvodní odstavce kapitol:"AI is rapidly changing the way we think about photography. Just a couple of years from now, most advances in the photo space will be AI-centric, and not optics or sensor-centric as before. The advancement in photography technology will, for the first time ever, be untethered from physics, and will create a whole new way of thinking about photography. This is how it's going to happen.Processing powerJust six months ago we saw the first glimpse of AI entering our consumer world when Apple introduced A11 Bionic neural engine chip, which powers current generation of iPhones. The A11 is important because the chip is specifically designed for tasks such as image–and face–recognition, AR applications, etc. In applications like this, it’s way more effective.
----cont. ....

Catering to the pros
But in professional and semi-pro setting, there are several other developments that are key to image quality. First of all, is the processing part, that has to happen right after the photo has been taken. Advances in RAW processing have been steady and predictable (but yet, very welcome by everyone), but AI is ready to supercharge this process. Recently PetaPixel featured a research paper named “Learning to See in the Dark” by Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun, that covers techniques of recovery of extremely underexposed RAW files. ... cont. ....
Photo optimization
One intriguing technology I had a chance to see recently is AI-powered upscaling, far beyond in quality than what is currently available to the public. A team of AI developers at Skylum is putting finishing touches on technology that will allow smartphone images to be upscaled and printed at an incredibly high resolution and sharpness. As I've previously pointed out, not everyone has an iPhone X in their pocket — hundreds of millions of people today are buying brand new phones that use 4-year-old technology, so having sharper, crispier photos from outdated smartphone sensors will allow millions of people future-proof their precious moments.
.....cont...
Závěr_

"After a long technological hiatus in image tech, we are yet again seeing an explosion of interest in the space. Photography plays an important role in every tech company, but nowhere it is more important than in the smartphone race. And as September edges closer, Google and Apple will both be aiming to announce cutting-edge photography advances. Yet, an influx of smaller players are innovating at a rapid rate and raising the stakes for everyone."

pátek 15. června 2018

Photolemur 2.3 Phoenix Update

Photolemur 2.3 Phoenix Update Everything You Need to Know
What's new for Windows Users?
www.photolemur.com

New Photo Processing Engine - Perfect Eye
This technology is powered by artificial intelligence and was tested on 120,000 images by 65 photographers. It examines the color of each pixel’s neighbors in the grid and automatically makes the hues look vivid and natural. 
New JPEG Processing Algorithm
With a new algorithm we made Photolemur processing more smooth and professional, and your JPEG images results even better.
Advanced Settings for Export
The new Photolemur Export Window allows you to resize images and manage their naming, format, and quality. You can also change the color profile of your photos and save all these settings to your own presets.
New Languages support
Photolemur now speaks two new languages: hebrew and arabic. 
Performance and stability improvements
Bug and crash fixes, fixes for various UI issues, Photoshop/Lightroom bugs fixes

Look Up Tables (LUTs) - aktuální téma

3D LUT Creator
Využití LUT ( Look-Up-Table) v barevných úpravách fotografií se stává stále aktuálnějším tématem.
V této souvislosti bych rád připomněl unikátní nástroj, o kterém jsem již pojednal ve dvou svých příspěvcích tohoto weblogu. Je jim 3D LUT Creator.
Co to je a čemu LUT slouží, se dozvíte v tomto mém weblogu,
https://digifoto.akamonitor.cz/2018/04/using-luts-here-is-what-you-need-to-know.html
nebo ve videu:"What is LUT" na adrese:  https://youtu.be/3ZpbUOGDWLE
Adresy mých dvou zmíněných příspěvků jsou:
https://digifoto.akamonitor.cz/2018/03/3d-lut-creator.html
https://digifoto.akamonitor.cz/2018/04/3d-lut-creator-all-in-one-slideshow.html
Adresa mé All-in-One Slideshow-review je: www.akamonitor.cz/sw/3dlutcreator
Adresa produktové stránky programu je: www.3dlutcreator.com
Adresa videa "3D LUT Creator Introuction", charakterizujícího produkt, je:  https://youtu.be/3tyYjsYUrww
Tvůrci programu uvádějí následující důvody, proč se rozhodnout pro aplikaci 3dlutcreator:  Cituji:"WHY USERS CHOOSE THE 3D LUT CREATOR?
Unique tools of 3D LUT Creator won't be found in any other photo or video editor.
The speed and ease of use has been appreciated by more than 5,000 users of this program.
Integration with Adobe Photoshop in a single click allows you to download LUT into Adobe Photoshop.
Ability to create LUTs was appreciated by videographers and colorists from around the world.
Constant updating of program's functions won't leave  anyone indifferent."
A velké překvapení nakonec!
Můžete si snadno vyzkoušet na svém mobilu nebo tabletu.

čtvrtek 14. června 2018

What’s new in Photolemur 2.3 Phoenix.

What’s new in Photolemur 2.3 Phoenix.
www.photolemur.com/windows
PerfectEyeTM - Processing Engine.
Supercharged Technology inspired by how the human eye sees reality. New engine inside the app provides the ability to improve 95% of all processed images. Our aim was to make all photos come out perfectly from your camera - the same way you saw the scene when you photographed it and avoid spoiling images by making them unrealistic.
Auto Lens Correction.
Distortion usually appears on images taken with wide lenses and causes objects to look different in size and shape to how they actually look in real life. Photolemur lens correction automatically fixes distortion as well as chromatic aberration and vignetting to make your image looks naturally.
JPG Fix.
JPEG images are straightened from garbled mess back into a clean, clear and crisp state. Photolemur JPEG Fix finds and corrects mistakes in JPEG images by suppressing compression artifacts to quickly improve the quality of pictures.
Huge Export - Options Improvement.
New Photolemur Export Window allows you to resize images and manage their naming, format, and quality. You can also change the color profile of your photos and save all these settings to your own presets.
Tech Requirements.
Windows 7, 8, 10 (64-bit)
2 GB of free hard-disk space
2 GB of RAM
1 GB of VRAM

úterý 12. června 2018

AI image recognition fooled by single pixel change

AI image recognition fooled by single pixel change 
BBC News - 3 November 2017
Celý článek najdete na adrese:
https://www.bbc.com/news/technology-41845878
Cituji části textu:
"Computers can be fooled into thinking a picture of a taxi is a dog just by changing one pixel, suggests research.
The limitations emerged from Japanese work on ways to fool widely used AI-based image recognition systems.
Many other scientists are now creating "adversarial" example images to expose the fragility of certain types of recognition software.
There is no quick and easy way to fix image recognition systems to stop them being fooled in this way, warn experts.
.....

Závěrečná věta článku:
"There is certainly something strange and interesting going on here, we just don't know exactly what it is yet," he said

AI Googlu dokáže rozeznat kvalitu fotografií

AI Googlu dokáže rozeznat kvalitu fotografií. Zároveň je i ohodnotí
AI Googlu se promění ve výtvarného kritika
Autor: David Trlica - 22.12.2017 
Celý text si lze prohlédnout na adrese_
https://www.svetandroida.cz/ai-google-hodnoceni-fotografie/
Cituji části textu:
AI Googlu už umí například rozeznat objekty na fotografiích, ale prozatím vám neřekne, jestli je pořízený snímek vhodný na sdílení. To se ale může změnit. Google odhalil novou funkci, ke které se využívá umělá inteligence.
Umělá inteligence bude posuzovat fotografie na základě několika bodů. Trénuje se v tom, aby poznala fotky, které může typický uživatel považovat za technický povedené a esteticky atraktivní.
Zároveň by měla v budoucnu navrhnout i úpravy, které zvýší vizuální kvalitu vašich fotek. 

pondělí 11. června 2018

Nová AI opraví fotky ještě před jejich pořízením

Nová AI Googlu a MIT opraví fotky ještě před jejich pořízením
Google tentokrát spolupracuje s prestižní MIT
Autor: David Trlica - Světandroida - 2.8.2017
Plné znění článku najdete na adrese:
https://www.svetandroida.cz/mit-ai-google-fotografie/
Cituji vybrané části textu článku:
"Google ve spolupráci s univerzitou MIT představil nové využití umělé inteligence a strojového učení. Hlavní změna oproti jiným AI zaměřených na fotoaparát je v tom, že fotografie bude vylepšovat v reálném čase ještě před pořízením. Mnohem méně se také využívá automatických úprav, což je funkce, kterou má již dnes mnoho aplikací." 
"Pro začátek se tým rozhodl naučit neuronovou síť 5000 obrázků, které retušovalo celkem pět fotografů. Díky tomu má AI základní vzorec, se kterým pak pracuje při retušování fotografií
Prozatím není jasné, kdy by se tato AI mohla objevit v komerční sféře, nebo rovnou v telefonech." 

What is AI Photo Camera?

Here's what the new buzzword in photography actually means
By Jamie Carter February 28, 2018 - digitalcameraworld
Plné znění článku najdete na adrese:
https://www.digitalcameraworld.com/features/what-is-an-ai-powered-camera
Cituji z textu článku:

"Artificial intelligence (AI) is everywhere, and if you haven't yet got an AI-powered smartphone, you probably soon will do. Is it all just marketing hubris, or is AI in a smartphone – and particularly, in its camera – something we should all aspire to have? With the term AI increasingly being used not only in smartphones, but in all kinds of cameras, it pays to know what AI is actually doing for your photos.
What is AI?
AI is a genre of computer science that examines if we can teach a computer to think or, at least, learn. It's generally split into subsets of technology that try to emulate what humans do, such as speech recognition, voice-to-text dictation, image recognition and face scanning, computer vision, and machine learning. What’s it got to do with cameras? Computational photography and time-saving photo editing, that’s what. And voice-activation.
- Voice-activated cameras
- AI software
- What is computational photography?
- Depth sensors and blurry backgrounds
- What about DSLRs?
Who is AI photography for?
Everyone. For starters, it’s about democratising photography. “In the past photography was the domain of those with the expertise of using a DSLR to create different types of images, and what AI has started to do is to make the effects and capabilities of more advanced photography available to more people,” says Fitzpatrick.
AI might not replace Lightroom and other image-editing programs, but it does stand to change editing for the photographer."

"AI is quickly becoming an overused term in the world of photography. Right now it largely applies to smartphone cameras, but the incredible algorithms and sheer level of automated software that the technology is allowing will soon prove irresistible to most of us. It may not be time to chuck out the DSLR quite yet, but AI seems set to change how we take photos. Not only that, but it could soon take charge of editing and curating our existing photography libraries too. It may be over-hyped and often a shorthand for what is nothing more than the latest, greatest advanced software, but AI is going to do something incredible for photographers; it’s going to free-up more of your time so you can take more, and better, photographs."

Software Review: Photolemur 2.2

Software Review: Photolemur 2.2 
PDN Online - March 8, 2018 - By Greg Scoblete
Celý text, včetně řady ukázkových záběrů, najdete na adrese:
https://www.pdnonline.com/gear/software/software-review-photolemur-2-2/
Cituji úvod a část záměru:
"Those who work with artificial intelligencetypically prefer to take a sunny view of its potential. In the optimistic take, AI liberates humanity from its unimaginative grunt work, freeing us to focus on more creative and engaging pursuits. (In the pessimistic take, AI gains consciousness and super intelligence, and destroys all of human civilization, but let’s not worry about that right now.)
Photolemur is definitely built around the first promise. Trained on over 1 million images, this AI-powered software promises to improve your images instantly with zero intervention on the user’s part beyond a drag and a drop. Has our AI liberation moment arrived?"
---
"But that’s not the point, really. Photolemur is a tool for those who don’t want to labor over the Wacom tablet just to tweak and process RAW images—and it’s a pretty remarkable one at that. In minutes, you can process and improve dozens of RAW files for sharing on social media. Or, dump a batch of smartphone images into Photolemur and on the other end you’ll almost certainly have something better—with literally no work on your part. Score one for the machine."

Photolemur v.2.3 - Coming this Spring

Photolemur v.2.3 - Coming this Spring
Edit any volume of photos Automagically with Artificial Intelligence.
2x times faster. New image processing engine.
New version of Photolemur is powered by PerfectEye - proprietary AI-powered image processing engine.
The technology was tested and tuned on 120,000 images by 65 photographers of all kinds. The previous technology worked incredibly well with RAW images. The new technology is tuned to work well with JPEG images.
The Core
AI-powered image processing engine inside the app provides the ability to improve 90% of all processed images. One of our goals was to avoid spoiling images by making them unrealistic. The artistic look of your finalized images is your personal choice. Our aim was to make all photos come out perfectly from your camera - the same way you saw the scene when you photographed it.
Speed
Proprietary RAW-processing technology now is 2.5x times faster. Export speed for all types of images is 3x times faster. It was hard to achieve but we managed a great improvement.
JPEG
New engine works in different way with different types of images. New algorithm for JPEG images optimized for specific needs of this kind of images. JPEG images will become smoother, technology removes grain and JPEG artifacts from photos.


Learning to See in the Dark - Report

Learning to See in the Dark
Authors:
Chen Chen -UIUC, Qifeng Chen - Intel Labs, Jia Xu - Intel Labs, Vladlen Koltun - Intel Labs
Celý článek najdete  ve formátu PDF na adrese:
http://cchen156.web.engr.illinois.edu/paper/18CVPR_SID.pdf
Cituji abstrakt a závěr článku:
Abstract
Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learningbased pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fullyconvolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work.
-----

Discussion
We expect future work to yield further improvements in image quality, for example by systematically optimizing the network architecture and training procedure. We hope that the SID dataset and our experimental findings can stimulate and support such systematic investigation.

neděle 10. června 2018

AI Is Already Changing The Way We Think About Photography

AI Is Already Changing The Way We Think About Photography
MAY 30, 2018  - Evgeny Tchebotarev - forbes
Plné znění článku najdete na adrese:
https://www.forbes.com/sites/evgenytchebotarev/2018/05/30/ai-is-already-changing-the-way-we-think-about-photography/#6f8c8208bb6a
Cituji z obsahu článku:
"AI is rapidly changing the way we think about photography. Just a couple of years from now, most advances in the photo space will be AI-centric, and not optics or sensor-centric as before. The advancement in photography technology will, for the first time ever, be untethered from physics, and will create a whole new way of thinking about photography. This is how it's going to happen.
---
One intriguing technology I had a chance to see recently is AI-powered upscaling, far beyond in quality than what is currently available to the public. A team of AI developers at Skylum is putting finishing touches on technology that will allow smartphone images to be upscaled and printed at an incredibly high resolution and sharpness. As I've previously pointed out, not everyone has an iPhone X in their pocket — hundreds of millions of people today are buying brand new phones that use 4-year-old technology, so having sharper, crispier photos from outdated smartphone sensors will allow millions of people future-proof their precious moments.
---
Thousands of kilometers from Skylum AI research lab is another startup, that stealthily applying quantum mechanics research to RAW files, is promising to compress your photos up to 10x without loss of data.
---
After a long technologAical hiatus in image tech, we are yet again seeing an explosion of interest in the space. Photography plays an important role in every tech company, but nowhere it is more important than in the smartphone race. And as September edges closer, Google and Apple will both be aiming to announce cutting-edge photography advances. Yet, an influx of smaller players are innovating at a rapid rate and raising the stakes for everyone."

What's happening with AI and photography?

Could artificial intelligence disrupt the photography world?
TechRepublic - By Ant Pruitt | July 18, 2017,

Plné znění článku najdete na adrese:
https://www.techrepublic.com/article/can-artificial-intelligence-disrupt-the-photography-world/
Cituji z úvodu a ze závěru článku:
"In a recent blog post, a team at Google shared how its deep learning technology has been able to produce "professional quality" photo editing for a batch of landscape photos. In blind testing, pro photographers rated up to 40% of the images edited by AI as semi-pro or pro level quality. Quite frankly, some of the images published were quite nice, but is this enough to disrupt the world of photography? I don't think so. Disrupt the world of photography editing? Well it could be useful, but not disruptive. Allow me to explain."
---
SEE: The practical applications of AI: 6 videos (TechRepublic)
https://www.techrepublic.com/article/the-practical-applications-of-ai-6-videos/
---
"Conclusion
I think it would be tough for AI to know when and where to draw the line when it comes to post processing photos. Some photos need human intervention in the editing process to understand the mood and message the photo is supposed to convey, not just the adjusting of exposure or white balance. If a photo is just a run-of-the-mill landscape photograph, there just may be a place for AI photo editing. But even with that said, I'd much rather lean on the professional skills of landscape photographers."

AI is Taking Low-Light Photography to the Next Level

AI is Taking Low-Light Photography to the Next Level
MAY 09, 2018 - MICHAEL ZHANG - petapixel.com
Celý text článku najdete na adrese:
https://petapixel.com/2018/05/09/ai-is-taking-low-light-photo-quality-to-the-next-level/
Cituji z úvodu a ze závěru článku:
"When shooting a photo in low light, a low-ISO long-exposure photo requires a stable camera and blurs movement in the frame while a high-ISO short-exposure photo can be plagued with noise and poor quality. Now AI is bridging the cap, opening the door to low-ISO image quality while shooting at faster shutter speeds.
A group of researchers at the University of Illinois Urbana-Champaign and Intel have published a new paper titled Learning to See in the Dark. It explains how they trained an AI to do low-light image processing and produce results that are much cleaner and more usable than traditional high-ISO photos.
The team put together a set of photo pairs, with each pair containing a RAW short-exposure photo and a long-exposure version."
------
"You can find more comparison examples on the research project’s website and read the paper if you’d like to learn the technical details behind the experiment.
Experiments demonstrate promising results, with successful noise suppression and correct color transformation,” the researchers write, but they note that this is just the tip of the iceberg. The experiment lays the groundwork for much more exploration, including things like having the AI have what could be considered “Auto ISO” instead of having to provide the amplification ratio for each photo."

How AI computer vision is transforming photography

From phones to DSLRs, AI could help produce striking shots
By James O'Malley January 10, 2018 World of tech 
TechRadar
Celý článek najdete na adrese:
https://www.techradar.com/news/heres-how-ai-computer-vision-is-transforming-photography
Cituji z úvodu a ze závěru článku:
"Each year, we can be sure that the mobile industry’s hardware engineers have gone that little bit further in order to one-up the competition. Maybe an extra megapixel or two, maybe a better sensor, or a faster shutter.
But it is only within the last couple of years or so that this hardware arms race has been upset. The battle to create the best camera is no longer a question of hardware (though it doesn’t hurt). The real battle, thanks to the rise of artificial intelligence, is in software.
Today, the most exciting innovations in photography are not thanks to engineers tinkering with metal and glass - they are thanks to algorithms that are making our shots better than ever, and helping us stay organised in the process."
---
- Portrait mode battle
- Zoom and enhance
- Photoshopping central
---
!Sure, it might not be a good idea to have your key evidence in court based on images designed by AI - but at least it’ll make your low-res holiday snaps from 2003 look a little better when you print them.
So what’s clear is that in just a few short years, AI is transforming both the way we shoot photos - and how we edit them.
Perhaps the most exciting thing though is that this is just scratching the surface: Photography is just the beginning. As “computer vision” becomes an important, baked in part of other new technologies - such as self-driving cars - AI is going to become increasingly sophisticated when it comes to interpreting and understanding the contents of our images.
We don’t yet know how the tech industry will best make use of these new technologies - but what is clear is that in the future, your choice of camera app could be just as important as your choice of hardware."

AI and smartphone photography

AI is now starting a true revolution in smartphone camera technology.
Why AI looks set to take smartphone photography to the next level?
Africa's Technology News Leader - May 5, 2018 
Celý článek najdete na adrese:
http://www.itnewsafrica.com/2018/05/why-ai-looks-set-to-take-smartphone-photography-to-the-next-level/
Cituji z úvodu a závěru článku:
"AI has been making its presence felt in almost every arena of our lives and is now also taking the lead role in our smartphone cameras.
While our previous demands of our mobile cameras focused mainly on the number of megapixels and variety of filters, AI is now starting a true revolution in smartphone camera technology."
.........
"AI can also take the good old selfie to a whole new level with AI beautification. AI beautification provides 3D portrait lighting, making adjustments to better match the users’ facial features, resulting in luminous skin-tone enhancements and radiant selfies, even when backlit."

Photolemur - The first photo enhancer with brains

Welcome to the future of photography.
The Photolemur is Fully Automatic Photo Enhancer.
Photolemurs innovative algorithms are the heart of the magic. Photolemur thoroughly analyzes absolutely everything  (millions of pixels per second) and makes unique, specific adjustments to every last image.

With the Photolemur you can make your photos perfect with cutting-edge technology that automatically analyzes and adjusts everything it sees to restore lost details, touch up faces, and boost lighting and colors.

Photolemur has 12 smart technologies that help it to automatically analyze and adjust your photos. From faces and objects to colors, horizons, and the sky, it understands it all. 

And it works its tech magic from there. Photolemur naturally knows just what to do for images that wow. It analyzes and adjusts different aspects of the photo to achieve perfection. With a completely automated system, Photolemur gets you that epic end result faster than any human being.

Is Photolemur a photo editor?
To some extent, Yes - but authors prefer to call it a photo enhancer. The word editor’ is used when the software requires you to edit something manually. For example, using a photo editor requires additional skills and knowledge, as it has different tools and sliders that need to be set or adjusted. Editors are used mostly by professional photographers, who have the time and skills. Photolemur is an absolutely entirely automatic photo enhancer app that uses Artificial Intelligence to apply all the enhancements your image needs, on it's own. All you have to do is to import your image to the app, and the photo enhancer does everything else automatically from there.

A powerful interface.
Revolutionary user interface crafted by a Red Dot Award winning designer, Photolemur offers you the option to just drag & drop your photos and let the whole process of the photo editing be done by the technology itself. Forget about using sliders or complex controls that make editing a chore.

Automatic bulk picture enhancing.
Photolemur is an image editing app that is designed to dramatically simplify batch image editing: enhance all your images at onceprocess RAW fileswork with any volume of images. Its the absolutely stunning, fully automatic photo editing experience everyone has been waiting for.
Fits in any Workflow.

The power of artificial intelligence at your fingertips.
Innovative, user-centered interface puts all the focus on your images, and doesn’t confuse you with complex sliders. Sleek & simple on the outside, Photolemur houses the most advanced image processing technology on the inside. With the smart slider, you define the final look of your photos.

How it Works.
Step 1: Drop images.
Drag an image (or tons of images) into Photolemur. One simple drag and drop and in just a few moments, you’ll have stunning photos that will awe and amaze. You won’t believe you took them yourself.
Step 2: Watch Photolemur doing its magic.
Step 3: Define the final look of your photos.
Step 4: Epic end results, no expertise needed.

Photolemus is owned and loved by more than 30,000 casual photographers of all types and ages.
Photolemur is perfect for any Image.

SKYLUM Photolemur - All-in-One Slideshow-review

SKYLUM Photolemur
All-in-One Slideshow-review of the Photolemur
was published here: 
https://www.akamonitor.cz/sw/photolemurok/


Firma SKYLUM a umělá inteligence

Skylum introduces Skylum AI Lab and joins forces with Photolemur
Prvky umělé inteligence lze sice najít v řadě špičkových foto-programech, ale informace o vytvoření firemního týmu, věnovaného speciální problematice aplikace umělé inteligence ( AI ) ve fotografii, je příjemným překvapením a příslibem do budoucnosti. Speciální divize, zřízená ve firmě SKYLUM, využije všech dosavadních zkušeností, především vývojové práce na programu Photolemur. Free verzi programu Photolemus si můžete stáhnout na adrese:
Článek najdete na adrese: 
https://skylum.com/blog/skylum-introduces-skylum-ai-lab-and-joins-forces-with-photolemur
Uvádím několik vybraných odstavců
"Skylum Software doubles down on Artificial Intelligence by creating new Skylum AI Lab and joining forces with leading AI-based image editor, Photolemur.
---
We are forming a new research and development division of our company – Skylum AI Lab. This new division will work on artificial intelligence, machine learning, and neural networks.
---
Why Our AI is a Good Thing for Photographers
Our AI won’t make you any less of a photographer and will help many people see big improvements in their images and less time spent editing. AI won’t decide when, where or how to take the decisive image, or what is the best composition, framing option or lighting situation. It can’t ‘take over’ or take away our artistic decisions either.
---
What it can do is empower people, help them to unlock their creativity, and produce work they never imagined possible before. Our AI technologies make it possible to get stunning image results that can’t be created with camera settings or ordinary editing."

Photolemus technology

12 Essentials powers that improve your photography
Photolemur patří k prvním vlaštovkám uplatnění umělé inteligence ( AI ) ve fotografii.
Jeho výsledky při postprodukci jsou překvapivé!
Pokud vás bude zajímat více o uplatňované technologii, věnujte pozornost následující webové stránce:
https://photolemur.com/technology
Pro vaše pohodlí jsem vypsal odkazy na popisy jednotlivých nástrojů automatických úprav.
Direct links to 12 essentials powers: 
https://photolemur.com/technology/сolor_recovery
https://photolemur.com/sky_enhancement
https://photolemur.com/exposure_compensation
https://photolemur.com/smart_dehaze
https://photolemur.com/natural_lighting_correction
https://photolemur.com/foliage_enhancment
https://photolemur.com/noise_reduction
https://photolemur.com/tint_perfection
https://photolemur.com/face_retouching
https://photolemur.com/jpg_fix
https://photolemur.com/raw_processing