A group of scientists from Intel and the University of Illinois at Urbana–Champaign have published a paper called Learning to See in the Dark detailing a powerful machine-learning based image processing technique that allows regular cameras to take super-sharp pictures in very low light, without long exposures or the kinds of graininess associated with low-light photography.
The results are astounding.
We propose a new image processing pipeline that addresses the challenges of extreme low-light photography via
a data-driven approach. Specifically, we train deep neural
networks to learn the image processing pipeline for low-
light raw data, including color transformations, demosaic-
ing, noise reduction, and image enhancement. The pipeline
is trained end-to-end to avoid the noise amplification and
error accumulation that characterize traditional camera pro-
cessing pipelines in this regime.
Learning to See in the Dark [Chen Chen, Qifeng Chen, Jia Xu and Vladlen Koltun/Arxiv]
Learning to See in the Dark [Chen Chen, Qifeng Chen, Jia Xu and Vladlen Koltun/University of Illinois]
(via Four Short Links)
There’s still magic in the world, as evidenced by this fairy’s-eye view of Children’s Fairyland, that charming 70-year-old storybook theme park in Oakland, California. You might remember that when I’m not blogging, I work with Fairyland. WELL… months before we were mandated to shelter in place, a local photographer, Stephen Loewinsohn, contacted our team at […]
We’ve been writing about Lea Redmond since 2009 here on Boing Boing. She’s just one of those kind of people who consistently makes neat things — a real Happy Mutant! Well, her latest creative venture is Home Sweet Home, an activity deck for kids (and the young at heart). It offers inspiring prompts for whimsical, […]
Listed at $159,900 this 1,075 square-foot home in Pittsburgh, Pennsylvania is bland on the outside but features rooms with outer space, submarine, tropical island, and moonbase motifs. The owners put a lot of work into it!
Even in horrible economic times, a few simple rules hold unshakably true. And one of those rules is that if you possess an in-demand skill, you’ll always find work — and often, at a top market salary, to boot. If you understand Big Data and how to find order from the chaos of massive stockpiles […]
We live in a disposable era. If you can’t fix a broken item with a wrap of duct tape, there’s a very strong likelihood that its next destination is the trashcan. However, that probably leads to a trigger-finger death sentence for many household items that could be saved with just a bit more ingenuity. Before […]
Right tool for the right job. You probably heard a parent or grandparent say it at least once at some point. And it’s true in so many cases. If you spot a small tear in your living room curtains or near to hem a pair of pants, you can always use the good old fashioned […]