Archivi categoria: Software

Impressive Adobe Algorithm Transfers One Photo’s Style Onto Another

Two pairs of researchers from Cornell University and Adobe have teamed up and developed a “Deep Photo Style Transfer” algorithm that can automatically apply the style (read: color and lighting) of one photo to another. The early results are incredibly impressive and promising.

The software is an expansion on the tech used to transfer painting styles like Monet or Van Gogh to a photograph like the app Prisma. But instead of a painting, this program uses other photographs for reference.

“This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style,” says the rather technical abstract of the Deep Photo Style Transfer paper.

Put more plainly: when you put in two photographs, the neural network-powered program analyzes the color and quality of light in the reference photo, and pastes that photo’s characteristics onto the second. This includes things like weather, season, and time of day—theoretically, a winter’s day can be turned into summer, or a cloudy day into a glorious sunrise.

The team’s early examples show the program in action. So this original photo:

Plus this reference photo:

Equals this final photo:

It’s important to note that the software does not alter the structure of the photo in any way, so there’s no risk of distorting the lines, edges or perspective. The entire focus is on mimicking the color and light in order to copy the “look” or “style” of a reference photograph onto a new shot.

Since this is a lot easier said than done, the program has to intelligently compensate for differences between the donor and receiving image. If there is less sky visible in the receiving image, it will detect this difference and not cause the sky to spill over into the rest of the original shot, for example.

The software even attempts to “achieve very local drastic effects,” such as turning on the lights on individual skyscraper windows, all without altering the original photo by moving windows around or distorting edges.

Let’s look at one more example. Here’s the original winter landscape shot:

When you plug it into the Deep Style Transfer program with this summer landscape as a reference image:

You get this odd creation:

In the future, a perfected version of this technology could make its way into Photoshop as a tool, or run as a separate program or plug-in. Not that you should bank on this tech fixing the photos from your upcoming trip; like any other new technology, there is work to be done.

“The study shows that our algorithm produces the most faithful style transfer results more than 80% of the time,” the paper cautions. So maybe you can’t change Ansel Adam’s Moonrise, Hernandez to a Sunrise, Hernandez, but you get the picture (no pun intended) and it is very promising.

If you’re interested in digging into the tech behind this creation, read the full paper at this link.

(via DPReview)

Canon 5D Mark IV Firmware Update to Reduce 4K Crop from 1.74x to 1.27x

Rarely has a headline so technical been so genuinely exciting. In addition to the rumored addition of C-Log, a new report claims Canon will also significantly improve the crop factor for 4K video shot with the 5D Mark IV from 1.74x to just 1.27x, letting you take advantage of a lot more sensor.

The longer we wait, the more details come to light about Canon’s rumored firmware update for the 5D Mark IV. We already told you about C-Log, but according to a new report by Canon Rumors, the video capability of the full-frame camera will be improved even further with this update, especially where 4K shooting is concerned.

Some highlights:

  • DCI 4K resolution will be increased to 5632 x 2970 or 1.27x crop factor.
  • UHD will go up to 5472 x 3078, or 1.29x.
  • 1:1 4K sampling will remain an option for those who want to use the 1.74x crop
  • Canon will add full-sensor 3K capture at 60fps and HDR 24fps.
  • 1080p will also use this same 3K mode, down-sampled to 1080 for improved perceived resolution.

Additionally, CR received more details about the rumor that you will need to send your camera into a service center for these updates. It sounds like, from this new report, you will not necessarily need to do this.

The new firmware will work on non-serviced cameras, but there’s a chance the camera will overheat. If you want to avoid this, you’ll be able to send your Canon 5D Mark IV in to be retrofitted with a better heat sink. All new models, meanwhile, will ship with the better heat sink already installed.

For now, none of this has been confirmed or officially released by Canon, so take it with the appropriate amount of repressed hopes. We’ll keep an eye out, and let you know as soon as any of this news becomes official.

Free Cactus Firmware Lets You Use HSS and TTL with Different Flashes and Camera Systems

Photographers using Cactus‘ new V6 II and V6 IIs wireless flash transceivers are about to get a huge update. Cactus is launching a series of brand-specific firmware upgrades that will allow you to mix and match camera and flash brands without losing TTL or HSS… and they’re free!

Cactus’ new transceivers already promise cross-brand High Speed Sync (HSS) with some of the biggest names in the industry. The so-called “X-TTL” updates will expand that capability even further, allowing you to maintain Through The Lens Metering (TTL) with Canon, Nikon, Olympus, and Panasonic flashes (or compatible third party flashes for these systems) when you use them with Sigma, Sony, Fujifilm, Canon, Nikon, Olympus, Panasonic or Pentax cameras.

In other words, you could use your Canon flash with your Fujifilm camera, and thanks to Cactus transceiver and this firmware update, you’d still be able to use TTL and HSS no problem. The tagline is “TTL without boundaries.”

According to the press release, the firmware updates will roll out in parts. The first rollout will go out to Sigma, Fujifilm, and Sony camera users, followed by “the remaining camera systems,” namely: Canon, Nikon, Olympus, Panasonic, and Pentax.

No word yet on when exactly the X-TTL updates will begin rolling out, but this website will keep you up to date. Once the free updates are live, all you’ll have to do is download the Cactus Firmware Updater and select your camera system to install the X-TTL firmware on your V6 II or V6 IIs.

(via DIYP)

Fujifilm X-T2/X-Pro2 Firmware Update to Bring 33 Improvements

Fujifilm has a history of releasing firmware updates so significant that you feel like you’re downloading a brand new camera. The company has just announced this type of upcoming update to the X-T2 and X-Pro2: the new firmware will bring a whopping 33 functional and operational improvements.

The updating will occur via two different firmware updates released in late March and late May. The improvements reflect “users’ requests for improving operability and adding new functions,” Fuji says.

There will be a brand new Voice Memo function that lets you record 30-second audio clips while in Playback mode, useful for saving some “notes” for photos to reference later.

There’s also going to be a new Copyright Info feature that lets you register the photographer and copyright holder’s name(s) in advance so that those details are automatically baked into the EXIF data of each photo.

Here’s a complete list of the big improvements headed your way if you own one of these two flagship X Series cameras:

March 2017 Update

1. Shooting RAW in Bracketing and Advanced Filters
The update enables you to use the RAW format when shooting not only in AE Bracketing but also in other Bracketing modes (ISO, Dynamic Range, White Balance, Film Simulaitons) and also in Advanced Filter modes.

2. Extended ISO 125 and 160 selectable
The update adds ISO125 and ISO160 to extended ISO levels available.

3. Programmable long exposure of up to 15 minutes
Long exposure in the T mode currently goes only up to 30 seconds. The update will allow users to extend it up to 15 minutes.

4. ON/OFF for 1/3-step shutter speed adjustment (X-T2 only – already in X-Pro2)
The update allows you to turn off the Command Dial’s function to adjust shutter speed by 1/3 steps in order to prevent unintended adjustments.

5. Full-range ISO adjustments with the Command Dial (X-T2 only)
With the update, set the ISO “A” position to “Command” to adjust ISO sensitivity across the full range, including extended ISOs, with the Front Command Dial.

6. “AUTO” setting added for the minimum shutter speed in the ISO Auto setting
The update adds an AUTO option for the minimum shutter speed in the ISO Auto setting, that allows the camera to automatically define the minimum shutter speed according to the focal length of the lens attached.

7. Faster “Face Detection AF”
The update enables the use of Phase Detection AF for faster performance in Face Detection AF.

8. Improved in-focus indication in the AF-C mode
The update reduces focus hunting in the AF-C mode, making it easier to track a subject.

9. Addition of a smaller Focus Point size in Single Point AF
The update adds a smaller Focus Point size in Single Point AF, bringing the total number of available sizes to six. The new smallest size facilitates pin-point focusing.

10. Addition of “AF Point Display” (X-Pro2 only – already on X-T2)
With the update, you can choose to have AF Points constantly displayed in Zone AF and Wide / Tracking AF, making it easier to track a subject.

11. Addition of “AF-C Custom Setting” (X-Pro2 only – already on X-T2)
The update adds “AF-C Custom Setting” for specifying focus-tracking characteristics. Choose from five presets according to your subject’s type of movements.

12. Addition of “Portrait / Landscape AF Mode Switching” (X-T2 only)
The update allows you to specify separate AF mode and AF point settings for portrait orientation and landscape orientation.

13. Change of focus frame position while enlarging it
The update allows you to move the position of focus frame while enlarging it in Single Point in the AF-S mode or in the Manual Focus

14. Activation of the Eye Sensor in video recording (X-T2 only)
The update allows you to use the Eye Sensor during video recording to automatically switch between EVF and LCD.

15. Change of ISO sensitivity during video recording (X-T2 only)
The update allows you to change ISO setting during video recording.

16. Re-autofocusing in video recording
With the update, half-press the Shutter Release button or press the button assigned to “AF-ON” function during video recording to re-do autofocusing.

17. Display live histogram during video recording (X-T2 only)
The update allows you to display a live histogram during video recording.

18. Optimization of external microphone’s input level (X-T2 only)
The update optimizes external microphone’s input level (lower limit revised from -12dB to 20dB) to reduce white noise when an external microphone with preamp is connected.

19. Addition of “Eye Sensor + LCD Image Display” in the View Mode
The update gives the “Eye Sensor + LCD Image Display” option in the View Mode that allows you to shoot through the viewfinder and check images on the LCD, just as you would with an SLR.

20. Shorter EVF display time-lag (X-Pro2 only – already in X-T2)
The update shortens EVF’s display time-lag in the AF-C mode so that you will not miss a photo opportunity.

21. Constant “Dual” mode display (X-T2 only)
With the update, the small window in the Dual mode stays on even when you half-press the shutter release button.

22. Automatic vertical GUI for LCD (X-T2 only)
With the update, when you hold the camera in the portrait orientation, the camera will automatically display the GUI on the LCD in the same orientation.

23. Name Custom Settings
The update allows you to assign a specific name to Custom Settings 1 – 7.

24. Copyright information in EXIF data
The update allows you to register the photographer’s name and the copyright holder’s name in advance so that the camera automatically adds the information to EXIF data for each image.

25. Voice Memo function
The update enable you to record 30-second “Voice Memo” clips in the Playback mode.

26. Extended AE Bracketing
The update extends AE Bracketing from the current 3 frames +/-2EV to up to 9 frames +/-3EV.

27. Addition of “Shoot Without Card” mode
With the update, you can have the “Shoot Without Card” mode turned OFF so that the camera can not shoot when there is no SD card inserted.

May 2017 Update

28. Support for computer tethering via Wi-Fi (X-T2 only)
The update adds support for computer tethering via Wi-Fi.

29. Addition of “All” AF mode (X-T2 only)
With the update, select “All” in the AF mode so that you can select the AF mode and Focus Area size by only using the Command Dial.

30. Function extension for “Shutter AF” and “Shutter AE” (X-T2 only)
With the update, you can specify different settings for AF-S and AF-C in “Shutter AF” and for AF-S / MF and AF-C in “Shutter AE.”

31. Addition of “-6” and “-7” to EVF’s brightness setting
Additional options of “-6” and “-7” to the “EVF Brightness” setting so that, even in an extremely low-light condition, the brightness of the EVF does not distract you from shooting.

32. Switchover of the main and sub displays in the Dual Display mode (X-T2 only)
The update allows you to switch between the main and sub displays in the Dual Display mode.

33. Function assignment to the Rear Command Dial
With the update, you can assign a specific function to be activated when the Rear Command Dial is pressed.

Adobe’s New Algorithm Makes Super Difficult Selections a Cinch

Adobe Research has been working on some pretty interesting photo and video editing features, but their latest research might just revolutionize photo editing as we know it. Imagine if Photoshop could automatically cut out complex subjects in seconds, no matter the background… no pen tool required.

Adobe’s selection tools have caught a lot of flack—especially the new Select and Mask environment—but this research intends to silence all the naysayers. Using a two-part process that involves a “deep convolutional encoder-decoder network” and a “small convolutional network,” Adobe can cut out any subject from in front of any background with ease and accuracy.

Keep in mind, this is 100% software-driven; there are no dual camera systems, green screens, or manual selection tricks required to make it work. And it works like gangbusters! In the example below, the original image is on the far left, the second and third images use competing methods, and the far right image is the mask created by Adobe’s software:

The accuracy demonstrated here and in latter examples in the full research paper is impressive to say the very least. Fine hair is cut out of complex and similarly-colored backgrounds with insane accuracy, and Adobe’s system seems to beat every other competing approach hands down.

The research team applied their approach to 1,000 test images after training their neural nets with a data set of 49,300 images, and the algorithm seems to have learned well.

While we have no idea when this research will make its way into a future version of Photoshop or After Effects, the impact of highly-accurate automatic selection and masking tool is not to be underestimated. Read the full paper for yourself at this link, and keep an eye out for some incredible advances from Adobe in the coming months and years.

(via DIYP)

7 Tips for Making Lightroom Run Faster

Not happy with Lightroom’s sluggish performance on your computer? Here’s a helpful 15-minute video in which photographer and instructor Anthony Morganti shares a number of helpful tips for optimizing your Lightroom’s performance.

The tips are various settings you can adjust and tools you can run inside Lightroom, from Catalog Settings to Preferences and more. Since photographers have different workflows and needs, customizing how Lightroom runs can help make it run faster for your own purposes.

Here’s a quick breakdown of the main performance optimization tips discussed in-depth in the video:

#1. Build 1:1 Previews: Make Lightroom create a 1:1 preview of your photo files, trading extra disk space and slower importing for faster performance while working with your photos.

#2: Discard Previews: Have Lightroom automatically discard your 1:1 previews after a certain number of days to free up disk space.

#3: Preview Size and Quality: Make sure your preview size and quality and set to appropriate settings for your monitor.

#4: Camera Raw Cache Settings: Increase your cache size as large as you can from the default of 1GB.

#5: Use Graphics Professor: Try enabling or disabling the use of your graphics processor to see if that improves performance.

#6: Smart Previews: You can give up disk space and editing quality by using Smart Previews for faster performance.

#7: Optimize Catalog: Use the built-in optimization tool to keep things humming along over time.

Watch the video at the top of the post for a more detailed look at how you can make these adjustments and what they can do for you.

The video is episode #92 in Morganti’s helpful Lightroom Quick Tips video series. You can find his entire collection of videos on his YouTube channel.

(via Anthony Morganti via Fstoppers)

Sony Unveils Cool ‘Digital Filter’ App: An In-Camera Graduated ND Filter

Sony has just released an interesting new app for its mirrorless and high-end compact cameras. The app, called “Digital Filter,” lets you divide your sensor into up to 3 sections and capture each of those parts differently. It’s like a graduated ND filter built right into your camera’s software.

Actually, it’s more than a grad. When you open up the app, you get several options: Graduated ND, Reverse Graduated ND, Color Stripe, Blue Sky, Sunset, and two Custom options for setting up your own presets. The presets will capture preset exposure and white balance values, and if you pick Custom, you can adjust the location and feathering of each boundary, the effect above and below that boundary, and more!

Here’s a video demo that shows exactly how it works, step-by-step:

Exposure compensation, aperture, shutter speed, ISO, and white balance can all be adjusted for each individual section of the image. Then, when you press the shutter, each section is captured separately and merged in-camera. It’s basically a powerful, customizable in-camera HDR capture and merge app.

The app could come in very handy; the only catch is that you’re gonna have to pay up for it. Version 1.0 just went up on the PlayMemories app store for a whopping $30.

That might be a deal breaker for some, but if you’re interested in adding some in-camera HDR capabilities to your Sony without carrying around a bunch of Graduated ND and Reverse Grad filters, this app might be the way to go. To find our more or purchase the app for your Sony, click here.

(via Sony Alpha Rumors)