petapixel (unofficial)
OpenAI’s New Tech Lets You Generate Any ‘Photo’ By Just Describing It
#news #technology #ai #artificialintelligence #artificialintelligenceediting #artificialintelligencephotos #dalle2 #openai
Texas Sues Facebook for Billions Over Facial Recognition Violations
#culture #law #news #artificialintelligence #artificialintelligencephotos #facebook #facerecognition #facialrecognition #iptc #lawsuit #meta #metadata #socialnetworks #texas
These Are the First 100% AI-Generated Stock Photos of People
Smarterpix, Germany's leading stock photo agency, has announced an industry-first: a set of stock portraits that are 100% generated by artificial intelligence (AI) and available for legal licensing.
Smarterpix is operated by PantherMedia, the first microstock agency in Germany, which partnered with VAIsual, a technology company that pioneers algorithms and solutions to generate synthetic licensed stock media. The two have come together to offer the first set of 100% AI-generated, licensable stock photos of "people."
None of the photos are of people who actually exist.
AI-Generated, Human Portraits
PantherMedia says that phase one of its partnership with VAIsual will see a library of human portraits appear on Smarterpix, all of which can be generated with a green-screen background which allows them to be easily merged or inserted with other synthetic elements or real-life photography backgrounds to create entirely new content.
VAIsual's CEO Michael Osterreider believes that synthetic content -- photography that is generated by algorithms -- are the future of the stock photo industry. He estimates that within the next five to 10 years, 95% of all images will be AI-generated media.
"Our portrait library contains an ever-growing volume of diverse faces, ages, ethnicities, and genders," Osterrieder said. "We are aggressively working on our next phase of development and will shortly begin generating full-body images of humans."
"The time has come to move into new territory in the stock photo business for us, and AI-generated images will rapidly become a new standard element in the industry,” PantherMedia's CEO Robert Walthers says. He agrees with Osterreider's belief in a near future of mostly AI-generated photography.
Results May Vary
That isn't to say these photos are flawless. PantherMedia provided a set of nearly 800 photos made by the VAIsual AI and while many of them look very convincing, others, like the ones below, clearly need more time in the oven.
The emotions on display in this initial set of images are also limited. While disgust, boredom, or sadness are quite common, none of the example images appear to show happiness. Why this is the case was not explained.
No Model Release Required
The two companies aren't dissuaded by a few badly generated images and are betting the future on the technology. PantherMedia argues that the AI-generated portraits that are now available represent the next generation of "frictionless content." The photos require no model release and can be used in any context, and those who download the images no longer have to double-check the terms of usage or fear expensive litigation.
"We are the clean data guys," Osterrieder continues. "We produce all of our datasets in-house and own the copyright to all our synthetic creation. The real-life models used to create the datasets signed biometric release forms. The result is legally clean datasets, also available for licensing, and cost-efficient, litigation-free synthetic content."
PantherMedia expects the stock photo market to have an annual growth rate of 5% and projects global revenue in the space to grow to 4 billion dollars by 2023. Its bet on AI-generated content hinges on the technology being the easiest and most scalable and cost-effective solution to take advantage of the growing market.
#news #technology #ai #aigenerated #aiphotos #artificialintelligence #artificialintelligencephotos #panthermedia #smarterpix #stock #vaisual
NVIDIA’s AI Creates Realistic Photos Based Only on Text Descriptions
NVIDIA's GauGAN2 artificial intelligence (AI) can now use simple written phrases to generate a fitting photorealistic image. The deep-learning model is able to craft different scenes in just three or for words.
GauGAN is NVIDIA's AI program that was used to turn simple doodles into photorealistic masterpieces in 2019, a technology that was eventually turned into the NVIDIA Canvas app earlier this year. Now NVIDIA has advanced the AI even further to where it only needs a brief description in order to generate a "photo."
NVIDIA says that the deep learning model behind GauGAH allows anyone to make beautiful scenes, and now it's even easier than it ever has been. Users can simply type in a phrase like "sunset at a beach" and the AI will generate the scene in real time as each word is added. Adding an adjective like "sunset at a rocky beach" or swapping "sunset" for "afternoon" or "rainy day" and the model will modify the photo based on what is called generative adversarial networks (GAN).
"With the press of a button, users can generate a segmentation map, a high-level outline that shows the location of objects in the scene," NVIDIA says. "From there, they can switch to drawing, tweaking the scene with rough sketches using labels like sky, tree, rock, and river, allowing the smart paintbrush to incorporate these doodles into stunning images."
An AI-generated image created with the phrase, "a peaceful lake surrounded by tall trees in a foggy day."
NVIDIA says that the demo is one of the first to combine multiple modalities within a single GAN network. GauGan2 combines segmentation mapping, inpainting, and text-to-image generation in a single model which NVIDA says makes it a powerful tool to allow users to create photorealistic art with a mix of words and drawings. The goal is to make it faster and easier to turn an artist's vision into a high-quality AI-generated image. NVIDIA says that compared to other state-of-the-art models specifically for text-to-image or segmentation map-to-image applications, GauGAN2 produces a greater variety and higher-quality set of images.
"Rather than needing to draw out every element of an imagined scene, users can enter a brief phrase to quickly generate the key features and theme of an image, such as a snow-capped mountain range," NVIDIA says. "This starting point can then be customized with sketches to make a specific mountain taller or add a couple of trees in the foreground, or clouds in the sky."
An AI-generated image created with the phrase, "a tropical island with white sand beach view from above."
While the realistic image creation is probably the most impressive, GauGAN2 is not limited to that kind of recreation. Artists can also use the demo to depict otherworldly, fictional landscapes. NVIDIA shows a scene that recreates something akin to the Star Wars fictional planet of Tatooine, where the desert scene is initially created by the model but a second sun is added afterward.
An AI-generated image created with the phrase, "endless tall mountains in a sunny day."
"It’s an iterative process, where every word the user types into the text box adds more to the AI-created image."
The text-to-image feature can be tested on NVVIDIA AI Demos where anyone can try creating custom scenes with text prompts and further adjust them with quick sketches to create more refined results.
#news #technology #ai #aigenerated #aigeneratedscenes #aimodel #artificialintelligence #artificialintelligenceediting #artificialintelligencephotos #gan #gaugan2 #landscapephotos #nvidia #nvidiacanvas #nvidiagaugan2
Facebook is Shutting Down its Photo Face Recognition System
Facebook has announced that it is shuttering its Face Recognition system as part of what it is billing as a company-wide move to limit the use of facial recognition in its products.
Facebook Face Recognition is a system that is used to analyze the photos and videos that the company thinks a user is in on Facebook and it replaced the "tag suggestion" setting on the social network.
It uses a profile picture, photos, and videos that a user has been tagged in and assigned a unique number to that value. Then, for those who turn face recognition on in settings, Facebook uses that data as a template to compare against photos, videos, and other places a camera is used to recognize if that user appears in that content. Facebook says it never shared user templates with anyone.
Today, Facebook will begin to shut down the system. Users who have opted in to its use will no longer be automatically recognized in photos and videos and the company plans to delete more than a billion people's individual facial recognition templates. This change means that Facebook will end multiple services that rely on Face Recognition, which includes the Automatic Alt Text (ATT) system, which was used to create image descriptions for the blind and visually impaired.
"AAT currently identifies people in about 4% of photos. After the change, AAT will still be able to recognize how many people are in a photo, but will no longer attempt to identify who each person is using facial recognition," Facebook's VP of Artificial Intelligence Jerome Pesenti says. "Otherwise, AAT will continue to function normally, and we’ll work closely with the blind and visually impaired community on technologies to continually improve AAT."
Facebook may want to consider working in tandem with the International Press Telecommunications Council who recently announced that it would be updating metadata standards to help make photos more accessible to the blind.
It is unlikely that Facebook's choice to disband its Face Recognition system was done purely as a service to humanity. Engadget notes that Meta, at the time Facebook, settled a privacy lawsuit for $650 million in 2020 regarding facial recognition, and multiple governments around the world have either already passed or are considering at least partial bans on facial recognition use. Facebook and Meta very likely want to avoid any additional legal ramifications regarding Face Recognition, as that would compound the issues the company is already facing regarding the toxicity of its platforms for young people.
Image credits: Header image via Facebook.
#culture #news #artificialintelligence #artificialintelligencephotos #att #automaticalttext #facebook #facerecognition #facialrecognition #iptc #meta #metadata #shuttingdown #socialnetworks
NVIDIA Canvas Uses AI to Turn Your Doodles into ‘Photos’
NVIDIA has announced Canvas, an app that is available as a free beta that it says brings real-time painting tools to anyone with an NVIDIA RTX GPU. It uses artificial intelligence to make rudimentary sketches or doodles into photorealistic scenes.
Canvas is part of NVIDIA Studio, which is a program that provides artists and creators with both hardware and software tools to assist in bringing creative visions to life. Canvas appears to be the consumer-facing version of the app that NVIDIA showcased in 2019, but what is shown here is far more advanced than what was teased back then.
In Canvas, users can start sketching simple shapes and lines using a palate of 15 tools such as mountains, clouds, grass, or weather effects and the artificial intelligence model will turn those into a photorealistic scene in real-time.
What looks like a sketch made in Microsoft Paint is transformed into a lifelike scene instantly and with jaw-dropping quality.
"The tool allows artists to use style filters, changing a generated image to adopt the style of a particular painter," NVIDIA explains. "NVIDIA Canvas isn’t just stitching together pieces of other images, or cutting and pasting textures, but creating brand new images, just like an artist would."
The algorithm is aided by the tools palate in Canvas so that it understands what the artist is intending to show, but the results are still extremely impressive. NVIDIA says that the creative applications of the tool are "endless" and that it can help artists ideate faster than before, which is normally a far more time-consuming task.
Lines and shapes turn into life-like landscapes in seconds. | NVIDIA
"It can also bring time savings to a range of creators and designers," NVIDIA explains. "Consider an art director on a time crunch who needs to refine the hero product in an ad campaign. A landscape will complete the shot. Using NVIDIA Canvas, the director is only a few clicks from generating several beautifully rendered images. In a matter of moments, the tool provides multiple options for the client to review, saving precious time before finalizing the featured product."
https://www.nvidia.com/content/dam/en-zz/Solutions/studio/canvas/feature-1-630x354.webm
Canvas uses a form of artificial intelligence called "generative adversarial networks," or GAN. It is the same technology that NVIDIA has used in previous AI algorithms, like its tool that can create photorealistic faces. GANs consist of a generator and a discriminator that work together. A generator aims to convert material maps into images, and the discriminator understands certain aspects of what is generated. For example, the discriminator knows that water has reflections, and can tell the generator to create a representation of that.
"To deliver realistic portraits for artists, the GAN has been trained on an NVIDIA DGX system using over 5 million images," NVIDIA says.
The Canvas beta can be downloaded for free now, and NVIDIA is soliciting feedback on its forums.
#news #software #technology #ai #artificialintelligence #artificialintelligenceediting #artificialintelligencephotos #beta #canvasapp #gan #generativeadversarialnetworks #nvidia #nvidiacanvas
Deepfake Satellite Images Pose Risk to Global Politics and Military: Report
Fake, AI-generated satellite images can pose threat to nations and agencies worldwide, a team of researchers warns. These bogus images could be used to create hoaxes ranging from natural disasters to propping up other fake news, or even be used to mislead international governments into conflicts.
A Deepfake, which is a combination of "deep learning" and "fake," is synthetic media -- both photo and video content generated by artificial intelligence -- often created with the intention of fooling the content consumer. Although the content can be presented as a lighthearted joke in some situations, for example, when a TikTok user impersonated Tom Cruise, deepfakes can also cause issues of varying severity when used maliciously.
The Guardian reports that this type of false visual content is predominantly used for adult content, for example, to map a female celebrity's face onto the adult actor. It's also used to spread false news information or to scam individuals or businesses. In addition to falsifying existing information, deepfakes can create a non-existing person's profile from scratch, which can be further utilized for spying or for other deceitful or illegal means.
In August 2020, PetaPixel reported on the negative impact this type of manipulated media can have both on celebrities and on businesses who are impersonated and pointed out that detecting and keeping up with deepfake technology is a costly and difficult process for any research group that is prepared to tackle this.
However, deepfakes now also present a threat to nations and security agencies in the form of false and misleading satellite imagery, as first reported by The Verge. The bogus satellite images could be used to create hoaxes about natural disasters or to back up false news; it could also "be a national security issue, as geopolitical adversaries use fake satellite imagery to mislead foes."
A recent study, led by University of Washington researchers, examined this concern and "its potentials in transforming the human perception of the geographic world." The study points out that, although detection of deepfakes has had progress to an extent, there are no specific methods for detecting false satellite images in particular.
The team simulated their own deepfakes using Tacoma, Washington as a base map and placed onto it features extracted from Seattle, Washington and Beijing, China. The high rises from Beijing cast shadows in the fake satellite image while the low-rise buildings and greenery were superimposed from the urban landscape found in Seattle.
Study by Bo Zhao, et al. Fake satellite images of a neighborhood in Tacoma with landscape features of other cities. (a) The original CartoDB basemap tile; (b) the corresponding satellite image tile. The fake satellite image in the visual patterns of (c) Seattle and (d) Beijing.
The team explains that anyone unfamiliar with this type of technology would struggle to differentiate between real and fake results, especially because any odd details or colors can be attributed to poor image quality often found in satellite images. Instead, researchers note that to identify fakes, you can examine the images based on color histogram, spatial domains, and frequency domains.
The lead author of the study, Bo Zhao, explains that the study's goal was to raise public awareness of the technology that can be used to misinform and to encourage precautions, with a hope that this study can encourage the development of systems that could point out fake satellite images among real ones.
"As technology continues to evolve, this study aims to encourage more holistic understanding of geographic data and information so that we can demystify the question of absolute reliability of satellite images or other geospatial data," Zhao says to UW News.
Although AI-generated images could create chaos and loss for many security agencies and strategists, the researcher also points out that AI-generated satellite images can be used for positive purposes, too. For example, the technology can help to simulate locations from the past to study climate change, unrestricted growth in urban areas, known as urban sprawl, or how a region may develop in the future.
Image credits: Header photo licensed via Depositphotos.
#news #technology #ai #artificialintelligence #artificialintelligencephotos #deepfake #military #satelliteimages #satellitephoto
Vivo X60 Pro+ Review: Zeiss Onboard and Loaded for Bear
Vivo is positioning its X60 series as “professional photography flagship smartphones,” making clear that it wants to be regarded as the best mobile shooter available. With its partnership with Zeiss, it might have the tools to actually meet that goal.
In North America, it’s the likes of Google, Samsung, and Apple that command so many headlines, but a lot of the innovation in mobile photography is coming from Chinese brands. Alongside Vivo, others like Huawei, Xiaomi, OnePlus, and Oppo are among those testing the waters of what’s possible in phone photography.
For Vivo’s part, it throws out the word “professional” with confidence because -- as mentioned -- it partnered with Zeiss to co-engineer the imaging system in the X60 devices. The official word is that Zeiss primarily helped with lens design and system integration. This is why the phones have T* Coating and Tessar certification, and why Zeiss’s input is supposed to be evident in both the hardware and software.
I tested this out with the best of the bunch in the X60 Pro+, though some of the performance and results also apply to the X60 Pro.
Design and Build
This was my first time reviewing a Vivo device, so I went in with a clean slate of expectations, inside and out. From a design standpoint, it’s hard not to like the X60 Pro+. I last saw a (vegan) leather back on a phone years ago, and while its longevity may be in question after some wear and tear, the style certainly worked for me. Beyond that, it’s the camera array that stands out with four lenses and a prominent Zeiss logo visible at the top.
While I’ve never been fond of curved displays, even if they are somewhat subtle like the one here, the 6.56-inch Super AMOLED is objectively nice to look at. Its modest 2376 x 1080 resolution is something of a surprise for a flagship at this point, but it’s one of the corners Vivo cut to accommodate the 120Hz refresh rate. By default, it’s set to “Smart Switch,” which dynamically switches between 120Hz and 60Hz, and the company clearly spells out that it’s partly to preserve battery life.
There’s no wireless charging, though there is fast 55W wired charging — something I couldn’t test because my review unit came with a European charger. Under the hood, the phone runs on a Snapdragon 888 processor (the X60 Pro runs on the Snapdragon 870), and my unit had 12GB of RAM and 256GB of storage. There is an 8GB and 128GB variant as well. No memory card slot for storage expansion, either.
There is a unique “Extended RAM” feature that poaches 3GB of “idle” storage and allocates it to the existing RAM when the system requires it. It’s hard to know what would trigger it exactly, but the idea is to improve performance when multiple apps are running in the background. For context, the “+3GB RAM effect” would push this phone’s memory to 15GB under those circumstances.
Vivo’s plans to roll out the X60 series in North America are unclear. If the company does choose to, it would need to be a variant that supports 5G bands with local Sub-6 and mmWave support. As is, there’s virtually no compatibility, though 4G LTE should be fine.
Camera Features
Zeiss’s presence here is hard to measure because Vivo doesn’t always specify the extent with which its input applies. What is known is that T* Coating on the main camera is designed to reduce reflections, stray light, and ghosting. It’s the same type of coating Zeiss applies to its camera lenses, though this is not a first for a smartphone. Sony’s Xperia 1 II and Xperia Pro have also used the same thing already.
Vivo went with a 50MP 1/1.3-inch Ultra-sensing Samsung ISOCELL GN1 sensor with an f/1.57 aperture that is also capable of shooting at 100MP in High-Resolution mode. This 23mm equivalent lens and sensor are unique to the Pro+, as the regular Pro uses a 48MP Sony IMX598 as its main sensor instead.
The Samsung image sensor is not the same as the one in the Galaxy S21 Ultra, but rather the S20 Ultra, so it is a bit older than the most recent GN2 sensor. If there is any drawback in that, the Zeiss collaboration and onboard camera software is supposed to pick up any slack.
Going with this sensor also meant Vivo had to put its Gimbal Camera in the 48MP ultra-wide camera, which is a 14mm equivalent with a 114-degree field of view. It’s the same Sony IMX598 sensor that makes up the primary lens on the X60 Pro.
Perhaps in a reflection of the markets it is strongest in, Vivo prioritized portraits by assigning a 32MP telephoto lens to that mode. It’s a 50mm equivalent (2x optical zoom) trying to emulate a prime lens, and with an f/2.1 aperture and 0.8 Micron pixels, it works best when lighting is at least decent. Portrait modes and beauty features are vogue in other markets, which also explains why this phone has a “Male friendly makeup” option in the settings that is toggled on by default.
Rounding out the array is the 8MP telephoto lens, a periscope camera with a 5x optical zoom that is a 125mm equivalent with a tighter f/3.4 aperture. The Super Macro mode has its own setting within the interface, though there is an interesting discrepancy. While the Pro+ can get as close as 3.5cm, the regular Pro beats it by getting down to 2.5cm.
Software Features
Putting the hardware aside, there’s a lot happening with the software here. This is one of the busiest camera interfaces I’ve seen -- which is not a bad thing -- but does include a number of specialized choices. For instance, there are modes like Supermoon, Astro Mode, Pro Sports, Slow shutter, and Double exposure. These software-driven options may use one or more lenses to pull them off. And those are all under the “More” section. Never mind the seven (if you count Super Macro) that are laid out on the main camera screen.
It’s unclear just how much Zeiss had to do with any of that. Joint statements from both brands largely point to physical adjustments and certifications, with nary a mention of the influence over software. One exception to that includes using Zeiss’ Biotar portrait style for the Portrait mode. It aims to reproduce the classic bokeh effect, though makes it more selective, particularly after the fact under that mode.
Vivo also includes an AI Scene Optimization feature that adjusts settings based on the scene or subject, but I turned it off straightaway. When you’re presenting your device as a mobile photography arsenal, that kind of input wouldn’t be necessary for competent shooters. And since HDR figures so prominently — also as a selective option — there is plenty at work to try making photos look better.
It does run on Android 11, yet it’s Vivo’s Funtouch 11 overlay that makes more of a visual impression. The company’s newer OriginOS is only in China, so I have no basis of comparison, but in any case, the overall software experience isn’t bad. I did appreciate that my review unit didn’t have the kind of bloatware others have noted in other markets. That helped at least close the gap between the Funtouch overlay and stock Android. Still, compared to OnePlus’ OxygenOS, Vivo leaves plenty of room for improvement.
Image Quality
Main camera
As the biggest differentiator for the Pro+, the main camera is the key to the phone’s ability to shoot good images. It does better when conditions provide some color to the scene, and I noticed the contrast between photos with sunlight or vibrant hues, and those shot in overcast days or more neutral scenery. For the most part, though, photos come out looking really good, even upon closer inspection.
Like so many other phones these days, there is a tendency to overexpose when first setting focus, but adjusting the slider often leads to better results. There was no oversaturation nor overzealous sharpening to ruin the composition. I can’t say I was expecting that kind of restraint, though when a company promotes the photography prowess of its flagship phone, less is more sometimes.
And that’s kind of what’s happening with this camera because, as much as Vivo calls it a 50MP shooter, the standard Photo mode captures at 12.5MP. It shoots at 50MP in High-Resolution mode, using pixel binning to also support 100MP output, should you want to do that. It would’ve made more sense to integrate these things into Photo mode, with the option to choose from 12.5MP, 50MP, or 100MP.
The Zeiss T* coating did seem to have an effect on reducing glare, including lens flare when shooting towards light sources, but otherwise, I don’t know that it made a considerable difference in output.
Ultra-wide
The large ultra-wide camera has a lot going for it, except the most prominent elements are more impactful for video than for stills. Vivo’s Gimbal Stabilization 2.0 doesn’t do anything for photos, which is generally fine because the wider angle is less susceptible to movement for snapping images anyway.
What matters more, at least to me, is that there’s limited distortion. While not bad in that regard, there’s room for improvement, as I did note some degradation towards the edges. There is a fair bit of "lean" for objects close to the edges as well, but not enough to ruin the photos I took. Image quality was good, albeit with more muted color unless there was something really vibrant in the scene.
Telephoto and Hybrid Zoom
The 8MP telephoto periscope lens isn’t bad for something with a lower resolution that’s optically fixed at 5x zoom. It’s just that the limitations become obvious upon closer inspection. Vivo must be using some kind of sharpening to these photos to mask imperfections because they generally look more processed than others do.
With an f/3.4 aperture, it’s really handicapped in low-light situations, yet does come into play with some other modes that require multiple lenses, which I’ll get into later.
Vivo touts the 60x hybrid zoom, even though it really shouldn’t because it’s awful in just about every respect, standing no chance of producing anything remotely close to a usable image.
And unlike competitors, it offers no shortcuts to other hybrid focal lengths, so if you wanted to shoot at, say, 10x or 20x, you’d have to pinch-to-zoom to get there.
Portrait mode
The bokeh effect attached to the 32MP sensor and lens is interesting in that it supposedly harkens back to Zeiss’ heritage in optics. To whatever extent that’s actually true, it’s obvious Vivo’s software is doing the legwork here. You have the choice between 1x, 2x and 5x in Portrait mode, but 2x is the default because that’s the 50mm equivalent.
Once you take a shot, you don’t commit to the exact effect before, but rather after you’ve taken it. When I previewed portrait shots, I could drag the focal point around and adjust the level of bokeh with a slider that emulates F-stops along the way. The range is between f/0.95-16, with the background shifting accordingly. It always defaults to f/2.0 to start, which may be too creamy for the scene, whereas f/0.95 is on another level. The good news is you don’t have to commit to a bokeh level and stick with it. If you change your mind after, you can resave it again.
I’m often wary of modes like this, only to have come away impressed at the results here. In good conditions, especially outdoors, the phone produces images that are objectively nice. Despite some skin smoothening going on, skin texture is still visible, so it’s not done in a silly way.
Pro Mode
Off the bat, I appreciated Vivo at least trying to educate users on Pro features and terminology just by tapping the information icon in the interface. I could also appreciate that all four lenses were available to shoot within this mode, which isn’t always the case with other phones.
My one gripe is that the lens icons lay in really close proximity to the manual controls for exposure, ISO, shutter speed, white balance and autofocus. On several occasions, I accidentally picked a lens when I was trying to change ISO or shutter speed, leading to an annoying recalibration each time.
That aside, the mode shoots solid images, and while selecting RAW in the interface would make you think you’re solely capturing a RAW photo, it also saves a JPEG as well. Too bad Vivo didn’t think to include focus peaking, as that would’ve added to the overall composition. It’s a minor thing, and perhaps the company could add it through a software update in the future.
Night Mode
Where others talk a lot about night photography, Vivo is more understated. Its Night mode is okay, except there’s a lot of processing going on that leads to too much sharpening. HDR stacking combines multiple exposures to get an optimized image, like others do, only the results are highly contingent on available light.
Google and Huawei do it better, whereas Vivo is more in line with where OnePlus is currently. However, Vivo does offer something the others don’t, which is the ability to add some color variations to the composition. Under the mode, there’s a “Style” icon that brings up a menu of color balance filters. Select one and use the slider to adjust its intensity. For example, you have black & gold, green-orange, cyberpunk, and dark red, among others. I initially dismissed this as a gimmick -- and it is, to some degree -- yet was pleasantly surprised at how effective it could be.
In general, Night mode is somewhat autonomous in the sense that it also has an “extreme night” setting within it that kicks in whenever a scene is very dark. You can also shoot panoramic photos in this mode as well. Vivo adds Night separately in Video mode, making low-light photography and videography readily apparent throughout. It does need tweaking, though, and hopefully, Vivo improves it through software updates going forward.
Special Modes
With all the extras under the “More” section, the one that stuck out for me was Slow shutter. As its name implies, it emulates long-exposure photography that wouldn’t be possible to do manually on this device. Case in point, “Flow of traffic” captures light trails, and there are others that can capture fireworks, waterfalls, and more.
Along with the effect, you can also choose the exposure from as low as two seconds, and on up to 32 seconds. Fireworks switches to F-stops, since the idea is to freeze the bursts in action. Star Trails is really long exposure, starting at 30 minutes, all the way up to two hours, but to use that, you ideally need a darker sky to capture all the starry movements.
Supermoon was far better than I expected. It starts at 1x to combine the moon with a landscape scene, or you can zoom 10x, 30x, or 60x to get a closer take. In the former case, the main camera captures the landscape, while the telephoto camera shoots the moon. In the latter case while zooming, there’s a lot of software processing to make the image look detailed. The only caveat is that the moon needs to be unobstructed, or else the mode won’t recognize it. When I tried shooting it behind some tree branches, it never kicked in.
Double exposure is somewhat bizarre in that it combines the rear and front-cameras to overlay and blend them together. You can apply a couple of styles, along with a set of beauty features to smooth skin and whiten teeth. It’s an acquired taste, possibly yielding something useful in a rare circumstance.
Video Features
I didn’t go too in-depth in the video features, but they are pretty extensive. Video ignores the 5x telephoto lens and prioritizes the other three. It’s fine that 8K video is possible here, just that 4K at 30fps or 60fps is more versatile. Not without some limits, however. Turn HDR on and you’re limited to 30fps when shooting in 4K. The same is true if you turn on Super Night mode, which also won’t work at 60fps.
Movies is what Vivo calls a “Cinematic Master” feature that films in widescreen at a 2.35:1 aspect ratio, but the company oddly doesn’t include 24fps to the resolution options. To get that, you have to switch out of Video to Pro mode, tap the video icon, and select it from there. You don’t get the same aspect ratio, but at least you can control composition. Plus, you get focus peaking as an option, which you can’t do for still photos.
The Gimbal Stabilization 2.0 comes in under Video with the hand icon. Standard is the default, and you can go to Ultra if you need extra help, except you also get a little dip in quality that way. From my cursory testing while walking, both slowly and quickly, it’s an excellent feature, keeping footage steady throughout. Just unfortunate there’s no way to use it with Pro video (it does work with Movies).
Packed With Features That Need Time
I haven’t used too many smartphone cameras this feature-laden. It was like every time I launched the camera to shoot something, I discovered some new feature or option, and that’s why the interface requires time and patience due to how layered it is. Rather than stick most things into the settings menu, they’re available somewhere within the interface instead. That’s why it’s the kind of camera that you won’t fully understand until you take time to figure out where everything is, and how it works.
That can be a lot to take in for a novice, which is why this camera is overkill for anyone disinterested in learning to take better photos or video. Vivo is on to something with the full gamut available, somehow even making otherwise gimmicky modes look good. It just has to tweak certain things to make it even better. As for Zeiss, it needs to be clearer on exactly how it makes photos look better on the X60 series.
Are There Alternatives?
The X60 Pro matches almost everything the Pro+ does except for all the features related to the 50MP main and 8MP telephoto cameras. Zeiss was involved in developing the Pro’s camera array as well, though didn’t apply its T* Coating to its lenses.
As for others, the OnePlus 9 Pro is pretty extensive in its own right, though if you’re looking for a camera offering several modes, the Samsung Galaxy S21 Ultra is one of them. While far less versatile from a feature set point of view, the Google Pixel 5 is still an option, as would be the iPhone 12 Pro Max, which is Apple’s most varied camera array to date.
Should You Buy It?
Yes, so long as you’re okay with the fact 5G connectivity isn’t going to happen stateside. This is a phone built to connect at the highest levels elsewhere, but the camera can work anywhere, so it’s a worthwhile choice if mobile photography is of paramount importance.
#mobile #reviews #ai #artificialintelligencephotos #biotar #gimbalgamera #hdr10 #mobilereviews #nightmode #nightmodeai #smartphonereviews #stabilization #vivo #vivox60 #vivox60pro #vivox60proplus #vivox60proplusreview #zeiss #zeissbiotar
Vivo’s X60 Smartphone Series, a Collab with Zeiss, Launches Globally
Vivo has officially announced that its X60 series of flagship smartphones that it developed in collaboration with Zeiss is now available across major international markets. The X60, X60 Pro, and X60 Pro+ are the inaugural devices in the Zeiss x Vivo partnership.
Vivo originally announced the X60 series in China in January, but today the phones launch in multiple international markets.
Vivo says that the X60 series provides "professional-grade camera technologies" thanks to its co-engineering partnership with Zeiss. The company says that the partnership with Zeiss is mainly with lens design and system integration.
"To further redefine mobile photography, Vivo and ZEISS have co-engineered an imaging system that has passed the demanding quality management process by Zeiss, including original optical review, camera hardware testing, and actual photography verification," Vivo explains. "During this process, Vivo absorbed ZEISS’s optical design philosophy and ZEISS has also helped to optimize imaging on the X60 series."
Vivo says that the X60 series has passed the Zeiss certification process, including requirements to be labeled with ZEISS Optics marks such as T* and Tessar as a result of "the intense collaboration of R&D, design, quality, and testing experts." Vivo claims that the camera system delivers exceptional imaging effects through excellent aberration control, better image quality, and less stray light, ghosting, and other image artifacts.
"X60 Pro+ has certified compliance to Zeiss T* coating through further innovations on lens coating, which has a visibly improved light transmission, reduced reflections, and effectively achieved less stray light and ghosting and other image artifacts," the company continues. "As a result, the image quality is significantly enhanced. Moreover, X60 series has implemented Zeiss Biotar portrait style to reproduce the signature bokeh by leveraging advanced technologies including progressive bokeh simulation and distributed blurred spot rotation."
The Vivo X60 series marks the first time that any smartphone features the unique Zeiss Biotar "swirly bokeh" portrait style.
The X60 Pro+ has a quad-camera array that features a 50-megapixel, 48-megapixel, 32-megapixel, and 8-megapixel set of cameras. The X60 Pro has three cameras (48-megapixel, 32-megapixel, and 8-megapixel) plus a 32-megapixel front-facing camera.
The Pro+ utilizes what Vivo calls a "Dual Main Camera System" composed of that 50 MP Ultra-Sensing Samsung GN1 Sensor with f/1.57 large aperture and 100MP super HD mode, as well as a 48MP Ultra-Wide Gimbal Camera with 114-degree field of view for steady footage control. The below video is very likely a dramatization of the expected result.
Vivo combined electronic image stabilization with an extra Z-axis of rotation for image stabilization and now claims that the X60+ is capable of 5-axis video stabilization "effect" which should allow for more stable, clearer, smoother video and photo capture.
The X60+ also features what the company calls Pixel Shift Ultra HD imaging technology, which combines eight images taken in parallel to create extremely high-resolution finished files. This feature is available even when the camera is handheld, as the X60+ can actively correct for the motion of your hand during shooting.
"The X60 Pro and X60 Pro+ are equipped with Gimbal Stabilization 2.0. For X60 Pro, the Pixel Shift Ultra HD Imaging can be achieved through the gimbal camera system, while for X60 Pro+, its 48MP ultra-wide camera is equipped with the gimbal camera system, realizing 114° wide-angle capture. With it, there is no need for optical distortion correction to meet the super HD, ultra-wide night, and ultra-stable large field-of-view capture needs," Vivo says.
"Pixel Shift Ultra HD Imaging technology is creatively utilized, supplementing enhancement of image details and sharpness after eight pictures are taken in parallel to help users get ultra-HD images. After zoom resolution is enhanced, pixels are filled when zooming in to simulate higher-resolution optical zoom effect; moreover, Pixel Shift Ultra HD Imaging can replace the traditional demosaicing process to make details richer, reduce moiré patterns and minimize false colors as each pixel has more accurate RGB information, which ultimately brings superior capture experiences with clearer images and more accurate colors to users."
Vivo has also packed a set of other features into the camera capabilities, such as a sport mode that utilizes the gimbal camera and uses motion detection to track moving subjects, as well as a "Kids Snapshot" mode that is designed to capture ideal-light images of highly-mobile children. It also uses AI noise reduction algorithms to make for overall better low light photos and videos and supports a night mode and night portrait mode, night video mode, super panoramic mode with night scene HDR algorithms, and night scene wide-angle capture.
All the camera features are in addition to the slim design, 120hz refresh rate and 240Hz response rate running on an edge-to-edge AMOLED display that supports HDR10+. The X60 Pro + is powered by the Snapdragon 888 processor while the rest of the series runs on the Snapdragon 870.
For more details on the Vivo X60 series, you can read PetaPixel 's original coverage of the China launch here, but bear in mind there are some differences in what Vivo is offering between regions.
For example, the X60 Pro launched in China with a periscope camera -- which is still found on the X60 Pro+ for the global launch -- which is not found on the international version of the phone. When asked about its exclusion, Vivo said that it was left off due to "different needs and preferences of consumers in the global market."
International pricing was not specified per region at the time of announcement, but PetaPixel will update this story accordingly should that information be provided after publication.
#mobile #news #ai #artificialintelligencephotos #biotar #gimbalgamera #hdr10 #nightmode #nightmodeai #stabilization #vivo #vivox60 #vivox60pro #vivox60proplus #zeiss #zeissbiotar
