Feb 20, 2013– Santa Clara, USA (Techreleased) – Forging a path for the next wave of advanced, consumer-focused mobile imaging experiences and applications, NVIDIA today announced new capabilities delivered by the NVIDIA® Chimera™ Computational Photography Architecture.
Available in the NVIDIA® Tegra® 4 family of mobile processors, Chimera™ architecture offers a number of features never before available on mobile devices, including always-on high-dynamic range (HDR) photos and videos, HDR panoramic and persistent tap-to-track capabilities.
“We developed the Chimera Computational Photography Architecture to take mobile photography far beyond where it is today,” said Brian Cabral, Vice President of Computation Imaging at NVIDIA. “We’re enabling developers and users to not only use image processing to enhance their photos, but also use computer algorithms to create images no lens can capture alone.”
Previous mobile device architectures have made it difficult to use the best tools for different parts of complex image processing. Chimera architecture removes those boundaries by providing the power to conduct nearly 100 billion mathematical operations per second to perform image processing, using computational techniques used in X-ray CT scanners, deep space telescopes and spy satellites.
First revealed at CES 2013, the architecture redefines mobile imaging with always-on HDR photos and videos. This allows camera users to instantly capture high-quality, HDR images similar to how the human eye sees the world — in a vast array of locations and scenes, and under diverse lighting conditions.
Additional new features include HDR panoramic, which takes wide-angle, or “fish-eye,” shots that normally require an expensive digital single-lens reflex camera. The Chimera architecture captures a scene while the camera moves — from side to side, up and down or diagonally — effectively “painting” a panorama in real time from many angles and in any order the user wants. In contrast, competing offerings must either be moved in one direction along a single horizontal plane, or require significant amounts of post processing — taking up to 35 seconds — to stitch together the panorama.
In another industry first, the Chimera architecture includes persistent tap-to-track technology, which allows users to touch the image of a person or object to focus on within a scene. The camera then locks in on that subject whether it moves or the camera is repositioned to a better angle, while maintaining proper focus. Persistent tap-to-track also adjusts the camera exposure depending on any movement, helping avoid under- or over-exposure of the image’s subject or background.
NVIDIA Chimera is available as technology integrated into the Tegra 4 family, including Tegra 4 — the world’s fastest mobile processor — and the new Tegra 4i — the first integrated Tegra LTE processor.
Support from Leading Industry Players
Device makers can use the architecture to create differentiated imaging solutions to ship with their smart phones and tablets. The architecture also provides an application programming interface (API) that developers can use to create enhanced imaging apps for the growing Android mobile customer base.
Two important players in the camera imaging sensor market, Sony and Aptina — with others to be announced — have already added support for the Chimera Computational Photography Architecture. Sony’s Exmor RS IMX135 13 MP sensor and Aptina’s AR0833 1/3″ 8MP mobile imaging sensor support Chimera architecture, bringing always-on HDR capabilities to market. Device makers can now adopt this technology into their Tegra 4-powered devices; dramatically enhancing their photo and video capabilities.
“NVIDIA’s Chimera architecture with our AR0833 sensor delivers mobile customers an amazing photo and video experience,” said John Gerard, Senior Director of Mobile Products at Aptina.
Chimera Computational Photography Architecture Key Features:
- First always-on HDR photos and videos
- First HDR panorama
- First persistent tap-to-track technology
- First single-flash HDR capture
