How You Can Benefit from Computational Photography
5 Reasons you should consider doing computational photography
The lens. The shutter. The sensor. These three components are the fundamentals of a camera. And, for well over a century they were all you needed to capture the moment.
The algorithm. Now the fourth component of a camera, which augments the other three, drives computational photography to enhance colour, adjust focus and increase dynamic range and diminish artefacts. For over a decade, all these effects were possible in post-processing but now they can be done in real time on-camera using computational photography, giving multiple advantages for the new generation of creators.
In this article we’re looking at 5 beneficial features of on-camera computational photography.
An AI camera can enhance the mood, tone, texture and vibrancy of images and videos by combining the power of algorithms with popular photo-manipulation techniques allowing anyone to take stunning photos easily despite their skills in photography.
One such example is HDR (High Dynamic Range) imaging. It manipulates the exposure which causes an increase in vibrancy and contrast in photos. Computational photography also improves digital zoom by using deep learning to provide sharper detail without losing much image quality using an algorithm called super-resolution.
AUTOMATIC COLOUR CORRECTION & NOISE REDUCTION
Automatic colour correction is when software automatically adjusts the colours of an image to make it look more realistic and appealing. It can be used for anything from improving photographs taken in low light conditions to removing unwanted objects from the background.
Denoising in computational photography is a technique that reduces the appearance of noise in an image. It can reduce the visual distractions in an image and make it clearer, smoother, and better quality. Due to both advantages, photographers can take more realistic and better quality images anywhere bypassing the limitations of traditional photography.
“With color, we are using AI techniques to replicate the transformations performed by a skilled human retoucher automatically in real-time on the camera. These algorithms learn how to make local, context-aware adjustments to the image from large numbers of before/after pairs of processed images, and produce the sort of effects that have previously only been possible with skilled use of software like Lightroom.”
-Dr Liam Donovan, CTO of Photogram for the Phoblographer
“The software's tone-map was adjusted to bring out the colors in a low-light image that can't be perceived by the human eye in low-light situations. The results are hyper-real images that maintain the dark background of the surroundings, but feature more brilliant colors and detail than the human eye can process in real life.”
-Keith Kirkpatrick, 2019 (Communications ACM)
AUTO FOCUS & ELECTRONIC STABILISATION
Another key technology that has been deployed is autofocus (AF), which uses sophisticated pattern, color, brightness, and distance measurements from sensors in order to quickly determine where on your smartphone's screen your subject should be focused.
“The goal of AF is to help camera sensors recognize these objects, and then adjust the camera's focus settings automatically and quickly to allow them to track their typical movement, ensuring faster and more accurate focus tracking. "[Autofocus makes] focus easier for everything from sports to weddings to parents wanting to shoot their toddlers and kids,"
-Rishi Sanyal, science editor at Digital Photography Review.
Electronic stabilisation is a digital technique that uses computational photography to reduce the effects of camera shake. With electronic stabilisation, smartphones can do what DSLRs and camcorders can do (i.e. shoot videos and take photos without shaking).
“Smartphone cameras have smaller lens, sensor and body. They lack the specifications that would give them the same features as a DSLR. For that reason, computational imaging with the use of software allows smartphone camera apps to create effects that are typical in traditional cameras.”
Vincent Tabora for DIY Photography, 2021
VR, AR & MR
Virtual reality, augmented reality and mixed reality are all made possible through computation, giving way to new ways of storytelling and marketing our products and content. They have been used to create products that use interaction with a virtual world. And they have been used to create new ways of communicating with remote audiences.
The most popular type of computational photography is 3D imaging, but it has also been applied in AR, VR and MR environments.
In advertising campaigns, it has been used for 3D product visualisation which provides a more realistic view of the product than a 2D image would be able to. In medical imaging it has been used for MR imaging which relies on the same principles as CT scanning but without exposing the patient to x-rays or radiation that can be harmful over time.
ADAPTABILITY & CONNECTIVITY
In contrast to the heavy traditional cameras and outdated time-consuming image post-processing, computational cameras are adapting to the hectic lifestyles and workflows of the modern day creators by their seamless connectivity, real-time image processing, compact size and affordable cost.
“Four Thirds system uses a sensor about eight times bigger than a typical flagship smartphone, but four times smaller than a full-frame camera. By applying similar computational photography techniques to a sensor of this size, there is no reason that the already-excellent image quality of an MFT camera cannot be increased beyond the level of a larger full-frame camera, at a significantly lower cost and weight.”
Dr Liam Donovan, CTO of Photogram.
It’s safe to say that computational photography is fast becoming the future of photography. It is an emerging technology which has given birth to new types of cameras and tools that are making traditional photography more adaptive and flexible.
Foremost, it’s an expanding subject that can be improved and adjusted. This advantage allows us to be more transparent about the production of our Alice camera as well as more reactive towards our community. We are open for your suggestions and voice regarding what features you would like to be considered when building a creator’s dream camera. Join our Facebook group with over multi-dimensional 2000 creators who have already shared their voice, we want to hear yours!
Photos by Alice Camera Team
Wow, AI in photography. I would love to see more images to see how they come out!