Google RAISR uses machine learning for smarter upsampling
 |
Top: Original, Bottom: RAISR super-resolved 2x, Image: Google |
Upsampling techniques to create larger versions of low-resolution images have been around for a long time – at least as long as TV detectives have been asking computers to 'enhance' images. Common linear methods fill in new pixels using simple and fixed combinations of nearby existing pixel values, but fail to increase image detail. The engineers at Google's research lab have now created a new way of upsampling images that achieves noticeably better results than the previously existing methods.
RAISR (Rapid and Accurate Image Super-Resolution) uses machine learning to train an algorithm using pairs of images, one low-resolution, the other with a high pixel count. RAISR creates filters that can recreate image detail that is comparable to the original, when applied to each pixel of a low-resolution image. Filters are trained according to edge features that are found in specific small areas of images, including edge direction, edge strength and how directional the egde is. The training process with a database of 10000 image pairs takes approximately an hour.
Once RAISR has been trained it is capable of selecting the most appropriate filter for each pixel in a given low-resolution image to fill in new pixels in order to create a higher-resolution version. RAISR can also remove aliasing artifacts, such as moiré patterns or jagged lines in the low-resolution images when creating the larger version, something that linear methods are not capable of doing.
Eventually, Google may be able to use the technology to upsample images that are sent at mobile bandwidth-friendly resolutions. More information on RAISR is available on the Google Research Blog.
 |
Left: Original, Right: RAISR super-resolved 3x, Image. Google |
|
|
|
|
Nov 13, 2019
|
Nov 6, 2019
|
Oct 21, 2019
|
Oct 16, 2019
|
The Sony a7CR is a high-resolution addition to the company's compact full-frame a7C series. So what did we make of it and where does it leave the a7 IV that it sits just above?
Lomography's LomoChrome '92 is designed to mimic the look of classic drugstore film that used to fill family photo albums. As we discovered, to shoot with it is to embrace the unexpected, from strange color shifts to odd textures and oversized grain.
The LowePro PhotoSport Outdoor is a camera pack for photographers who also need a well-designed daypack for hiking and other outdoor use. If that sounds like you, the PhotoSport Outdoor may be a great choice, but as with any hybrid product, there are a few tradeoffs.
The Sony a7C II refreshes the compact full-frame with a 33MP sensor, the addition of a front control dial, a dedicated 'AI' processor, 10-bit 4K/60p video and more. It's a definite improvement, but it helps if you value its compact form.
Why is the Peak Design Everyday Backpack so widely used? A snazzy design? Exceptional utility? A combination of both? After testing one, it's clear why this bag deserves every accolade it's received.
If you want a compact camera that produces great quality photos without the hassle of changing lenses, there are plenty of choices available for every budget. Read on to find out which portable enthusiast compacts are our favorites.
What's the best camera for travel? Good travel cameras should be small, versatile, and offer good image quality. In this buying guide we've rounded-up several great cameras for travel and recommended the best.
'What's the best mirrorless camera?' We're glad you asked.
What’s the best camera for around $2000? This price point gives you access to some of the most all-round capable cameras available. Excellent image quality, powerful autofocus and great looking video are the least you can expect. We've picked the models that really stand out.
Above $2500 cameras tend to become increasingly specialized, making it difficult to select a 'best' option. We case our eye over the options costing more than $2500 but less than $4000, to find the best all-rounder.
Comments