Goto

Collaborating Authors

AOTH-NexOptic Technology Corp. joins Arm AI Partner Program

#artificialintelligence

From the primitive scratchings of ancient cave dwellers, to the super-high-resolution images of far-off galaxies captured by modern telescopes, human beings have always been obsessed with pictures. The history of photography is the progression of society's ability to freeze an image in time, using technology to gradually improve its quality. The word photography is based on the Greek "photos" and "graphe" which together means "drawing with light". While decent-quality photos today are instantly available with the touch of a button on any smart phone, early photography was a laborious process that often delivered poor results. Picture-making dates back to antiquity with the discovery of two principles – camera obscura image projection, and the observation that certain substances can be altered by exposure to light. Camera obscura, the phenomenon that occurs when an image is projected through a small hole onto an opposite surface, was found in the writings of Aristotle and Chinese scholars, dating back to the 4th century BC.


Interview: "The best image as fast as possible" – Motorola's approach to smartphone imaging

#artificialintelligence

Modern smartphones are essentially pocket-sized mini-computers, capable of dealing with many tasks that not very long ago would have been processed on desktop or laptop computers. The camera module is just one component of many, but more and more consumers are carefully considering camera performance in their buying decision. Manufacturers have been well aware for quite some time and are investing heavily to make sure the cameras on their devices can compete with the best. The device division of mobile communication pioneer Motorola for example, which was taken over by Chinese PC makers Lenovo in 2014, first assembled a dedicated camera and imaging team in 2013 when it was still part of Google. Since then the brand has launched a number of new devices in its Moto range with a clear focus on imaging performance and features.


Computational vs. traditional photography -- Complementary, not contradictory - DIY Photography

#artificialintelligence

There are now two ways of creating digital images with a camera. You can either follow a software-centric computational photography approach. The other way is to stick to traditional hardware-centric optical photography. The former is used with AI to help enhance the final image, the latter relies on the quality of the camera's components (e.g. The two techniques may differ, but they are not at all on a collision course.


Imaging the Propagation of Light Through Scenes at Picosecond Resolution

Communications of the ACM

We present a novel imaging technique, which we call femto-photography, to capture and visualize the propagation of light through table-top scenes with an effective exposure time of 1.85 ps per frame. This is equivalent to a resolution of about one half trillion frames per second; between frames, light travels approximately just 0.5 mm. Since cameras with such extreme shutter speed obviously do not exist, we first re-purpose modern imaging hardware to record an ensemble average of repeatable events that are synchronized to a streak sensor, in which the time of arrival of light from the scene is coded in one of the sensor's spatial dimensions. We then introduce reconstruction methods that allow us to visualize the propagation of femtosecond light pulses through the scenes. Given this fast resolution and the finite speed of light, we observe that the camera does not necessarily capture the events in the same order as they occur in reality: we thus introduce the notion of time-unwarping between the camera's and the world's space–time coordinate systems, to take this into account.


Visual 1st brings AI, AR, computational photography and more to light in 14 days!

#artificialintelligence

Visual 1st, the executive conference focused on promoting innovation and partnerships in the photo and video ecosystem, will bring AI, AR, computational photography, and the future of digital cameras to the center stage, Oct. 3-4, at the Golden Gate Club, San Francisco, Calif. AI is already everywhere in imaging, from recognition to enhancement to auto-editing – and of course, there's much more to come. In parallel, AR solutions are proliferating at a rapid pace, serving use cases ranging from having lots of fun to being highly productive. As these two technologies evolve in mutually reinforcing ways, we, as an industry, must take the imaging solutions they enable to the next level of value and profitability, while also keeping things safe, secure and private for our customers – but how? Alexander Schiffhauer recently left his role as Technical Advisor to Google's CEO Sundar Pichai to take product management responsibility for the company's computational photography teams. Under his leadership, these teams have pioneered innovation on Pixel Camera, leveraging AI and computer vision techniques to create photos unimaginable only a few years ago.