Google Super Resolution Zoom: Good Start but not There Yet

Our first testing of Google’s super resolution zoom recently announced in Pixel 3 shows that it indeed can restore some image details, but is still behind the best in class solutions.

Comparing to the “normal” digital zoom, which is basically an upscaling plus edge enhancement, Google’s zoom reveals some details that are indistinguishable in the “normal” image:

However, it’s still not the best of what super resolution can achieve. Below is a comparison of Google’s super resolution zoom to Almalence SuperSensor, a technique based on multi-frame super resolution, running on the same Pixel 3 smartphone:

It looks like Almalence SuperSensor is closer to be delivering on the “optical zoom” promise.

Another nice example captured when taking zoomed images of a book on optical design. Google super resolution makes the text somewhat better readable, however some characters still remain distorted beyond any possibility to recognize them. Also some minor color artefacts are introduced on the originally black text:

And again, if you really want to capture a readable text, Almalence SuperSensor is a solution (note that SuperSensor also got the white color of paper right):

Unfortunately, there is no way to reliably measure the Google’s super resolution processing time. It looks like the processing is performed in background. When trying to quickly open the image right after its icon appears in the camera app, the preview would still show a progress sign for a fraction of a second, probably implying that the image is still being processed. One can feel that the processing takes roughly one second altogether, but there is no way to verify that number. Almalence SuperSensor processing takes 200-500 ms on the same hardware (SnapDragon 845).

The full images used to make the above comparison examples are available in an archive below. Note: for accurate comparison the images of each scene were taken with the same Pixel 3 smartphone, from the same position under the same lighting. The zoom level might slightly differ between images as there is no way to precisely set the zoom factor in the Pixel 3 camera app. The Pixel 3 camera app, updated to the recent version as of Jan 25, 2018, was set to “HDR+” mode.

PS Stay tuned, we will soon show a comparison of super resolution zoom at video frame rates!

Google Super Resolution Zoom: Good Start but Long Way to Go

Please read the updated post.

After publishing this original post we were contacted by Google engineers who pointed to the fact that Super Res was not always on in the images we took. Of course, it happened unintentionally, there’s just no obvious way to make sure that Super Res kicks in when taking an image.

We have re-taken the test images as suggested by Google and we admit the results are much better now. However Almalence SuperSensor is still superior :).

Meet us at Mobile World Congress 2018

This year we will bring to MWC:

  • A live demo of our breakthrough VR quality improvement technology. An enabler for next generation high resolution HMDs, Almalence DLVR technology solves the problem of thin and lightweight optics quality without adding extra size or weight to VR/AR HMDs
  • Latest generation of mobile image and video improvement solutions. High resolution, lossless zoom, better low light performance and higher dynamic range plus image stabilization altogether in a single solution, available for both still image capturing and video/preview!
  • Next generation image and video improvement technologies to be brought to the market in 2018

Demo by invitation only. Please contact us to schedule a meeting.

xTeleZoom extends the lossless zoom range of iPhone 7+ dual camera

Computational imaging technology increases the resolution and enables high quality zoom beyond iPhone 7+ 2x telephoto camera hardware.

February 27, 2017. Barcelona.
Today at Mobile World Congress, Almalence, the leader in computational imaging technologies announced its xTeleZoom app for the iPhone, enabling extra high quality zoom capability. Using a sophisticated computational technique, the app is able to dramatically preserve resolution and suppress the noise while zooming.

Mobile phone photography is still limited in its ability to zoom in without sacrificing resolution and image detail. While there is no practical way to create an optical zoom solution in mobile form factor constraints, the phone makers, including Apple, add an extra telephoto camera to their devices to provide good zoom quality. This approach, however, is able to provide only a limited optical zoom factor as the longer focal length lenses in mobile size constraints suffer from decreased aperture, resulting in low resolution and high noise level.

“We developed xTeleZoom because even the most advanced hardware solutions alone cannot address the need for taking high quality zoom photos”, said Eugene Panich, CEO of Almalence. “The decreasing thickness of new phone generations poses bigger challenges on the lenses ability to zoom and resolve good image quality. Software like xTeleZoom is the only practical way to break the zoom quality barrier”.

Almalence’s xTeleZoom uses computational imaging technology that enables better zoom shots from the iPhone without compromised image quality. Originally developed for professional photography it’s now available as an iPhone app to extend the high quality zoom range of the telephoto camera of the iPhone 7+. The users of the iPhone 6, iPhone 6s and iPhone 7 models without a tele camera will also benefit from higher quality zoom using the xTeleZoom app.

xTeleZoom is available on iTunes for $.99: https://itunes.apple.com/us/app/xtele-zoom/id1189050574

xTeleZoom enables lossless zoom for iPhone

About Almalence
Almalence, an Intel Portfolio Company, is the global leader in computational imaging technologies used in a wide range of optical systems from high-end DSLR cameras to mobile phones. Almalence’s solutions are licensed by top smartphone OEMs. Almalence Inc. is a privately owned company with headquarters in Austin, Texas and the team distributed across the world – USA, Russia, Israel, China, and South Korea. For more information about Almalence technologies please visit www.almalence.com.

Almalence’s SuperSensor boosts mobile camera quality beyond physical limitations

Almalence Super Sensor LogoToday at the Embedded Vision Alliance meeting, Almalence has announced SuperSensor, a groundbreaking technology for integrated camera quality improvement without hardware modifications.

During the last few years mobile handset makers have been struggling to deliver the best image quality and advanced camera features. The camera has nearly become the number one feature of a mobile phone and the main thing that makes a difference for users. While the mobile camera quality seems to have nearly achieved its physical limitations, Almalence’s new technology is designed to give this a leap beyond confines.

SuperSensor Examples

Top: the font is too small, the illumination is too low and dynamic range is too high to capture the pictures.
Bottom: same scenes, same conditions, same camera, but with SuperSensor technology.

“Mobile handset makers always come to a point where camera quality improvement is impossible due to size restrictions or the cost, usually both”, says Eugene Panich, CEO of Almalence. “Using a computational component such as SuperSensor is a way to improve mobile camera features without adding a micron to its size and at just a small fraction of the cost of typical hardware improvement. While hardware improvements can take years to utilize, the time to market for a computational component could be as short as days, and you can even put it into the devices that are already sold via a system upgrade.”

Unlike other imaging solutions, each of which improves some specific property such as dynamic range or noise level only, SuperSensor provides complex improvements. Its effect is similar to replacing a 1/4” sensor with a 1/3” sensor containing more pixels, which results in higher resolution, lower noise, higher speed, and wider dynamic range altogether.

A demo of SuperSensor in a form of Android app for Nexus 5 is publicly available on Google Play. The first devices which utilize the Almalence SuperSensor technology are expected to be available on the market in 2015.

Further information, examples and demo can be found at: almalence.com/doc/super-sensor-demo

About Almalence
Almalence develops computational photography methods and imaging technologies that improve imaging quality and make advanced photography features available. Whether it is a mobile camera or a hi-end DSLR, a microscope or a satellite imaging system, Almalence’s solutions enable the improvement of basic image quality parameters such as resolution, low light performance, and dynamic range beyond the cameras’ physical limits. Almalence is a mobile imaging solutions provider for top mobile handset OEMs, a maker of the world’s best and unique desktop super resolution software and end-user mobile camera applications.

Rumors

Image Sensors World: Oppo Smartphone Snaps 50MP Pictures

Engadget has had a chance to test Oppo Find 7 smartphone camera – a high end smartphone long rumored to feature 50MP sensor.

Although it’s hard to tell for sure, but it looks like Oppo has licensed Almalence Super Zoom technology. There is a comparison of Almalence Superresolution Zoom with Sony Clear Image Zoom and an article on its implementation in Huawei phones.

Oppo-Find-7-super-zoom-2

Almalence’s new technology makes cameras see like human eye

Have you ever noticed that you see much more details when looking at a scene by eye than when seeing a photo of the same scene? If not, it’s just because it’s too common to be noticed. Even having, physically, a lower dynamic range than a camera, human eyes see more.

Almalence Dynamic Range Optimizer optimizes the usage of dynamic range of 8-bit images to make the most of image details visible. DRO uses a technique similar to tone mapping, exploiting the peculiarities of human vision. DRO can be used either for optimal conversion of RAW images into 8-bit RGB/YUV images or for improvement of existing 8-bit images.

Almalence Dynamic Range Optimizer reveals details in highlights and shadows. Automatic processing within milliseconds.

Same data acquired by the camera, different usage of dynamic range. Left: standard image produced by the camera. Right: result of Almalence DRO processing, close to what human eye would see. Details in shadows are revealed due to optimization of dynamic range usage. Noise is not amplified.

DRO is easy-to-integrate, extremely fast solution that automatically improves the images in 100% cases and can substitute HDR in most of cases.

Comparing to existing solutions aiming to provide similar improvements of digital imaging, Almalence DRO:

  • is faster by the order of magnitude, which allows to use it in mobile devices, for both still images and video
  • provides better quality, mainly due to absence of noise amplification in shadows
  • improves both shadows and highlights

Details in shadows are revealed due to optimization of dynamic range usage. Noise is not amplified.

Left: standard image, right: DRO processed (optimized) image. Details in both shadows and highlights are revealed due to optimization of dynamic range usage.

DRO can be integrated in ISP, camera drivers or applications.

Some comparison examples are available on our site: DRO_examples_Almalence_site.zip (33 MB)

Demo application is available upon request.

A Better Camera: alpha testers wanted!

For years we’ve been providing you with the most advanced imaging applications for Android. Now we have fused all our applications into a single multi-purpose camera app.

Moreover, we have made this application open source so that it should be backed with the power of Android developers community!

We are excited to invite you to become an tester of a very early alpha version of the application.

See the details on A Better Camera site