Prism AI emerges as one of the newest radiance field companies, focusing on leveraging Neural Radiance Fields (NeRF) and Gaussian Splatting to offer creative professionals new avenues for capturing and processing imagery.
Founded on the back of industry standstills and a burst of technological innovation, Prism AI represents a bridge between traditional visual storytelling and the future of digital creativity.
As we step into an in-depth conversation with Neirin Jones at Prism AI, we aim to peel back the layers of this startup’s journey, its foundational inspirations, and its vision for integrating these advanced imaging techniques into the mainstream. This discussion promises insights into not just the technicalities of what Prism AI does, but also the broader implications of its work for the creative industry.
Join us as we uncover the motivations, visions, and aspirations that drive Prism AI to reshape the landscape of visual expression.
What is Prism AI?
Prism AI is a new company that opens the creative photographic potential of NeRF, Gaussian Splatting, and the adjacent AI technologies to photographers, film, and image makers to capture their own original images and process them with AI. Radiance Fields are the inception of a completely new medium. We welcome any production or client who would like to work with this new technology.
Can you tell us about the journey of starting Prism AI in the radiance fields domain?
I have worked in film making at the highest level for two decades, first as a freelance DIT and DOP, and a Multi Camera Array Operator for specialist VFX 360 capture at Brownian Motion.
With the industry at a standstill last summer it seemed the best use of that time would be to dive head first into NeRF and 3DGS capture technique and processing. The result of that time was Prism AI, and I am very proud to say we have recently partnered with Clear Angle Studios - the industry standard for full body character scanning, head scanning, prop scanning, environment capture and 3D scan processing, so we are in a position to harness their incredible insight and depth of knowledge with both 3D and 4D capture and processing.
What inspired the founding of Prism AI?
Opportunity. Slightly ironically we are born out of the strike action in the film industry last year, which afforded us time that would never have been otherwise possible. Coupled with the technological explosion in developments at this time.
Also, I believe there is fantastic opportunity to be creative with this new method of image making from our own captured datasets. It will only be as good as the people who use it, and we want to be a platform for people to bring their ideas and creativity to it.
Can you share your Prism AI’s mission and vision? How do you see it evolving in the future?
Mission: Accessibility for image makers and creatives to be able to both capture the highest quality of images and data sets, but also to be able to visualize their stories in a completely new way.
We also believe that you don’t fully understand a process until you have broken it. Some of our most exciting forthcoming work has been where we deliberately set out to break the conventions of ‘good practice’. Some of our show-reel was shot on an iPhone - some of it on a 400+ camera rig designed specifically for NeRF capture. We want to encompass every potential technical opportunity to deliver the right results.
Vision: Meeting with people and showing them what is effectively 3D photography so far the part that gets the biggest reaction beyond the quality of the results, is when I send them a link direct to their iPhone, and they can visualize it in AR on their iPhone immediately in real time on a web browser (thanks to our colleagues at Vision3 for their web visualization capabilities).
I think the future is that the demand for photographic 3D and 4D visualization will grow exponentially with the onset of Apple Vision Pro, metaverse, etc… We want to create an environment for our clients to capture their creative vision and be able to deliver the highest quality imagery across both established pipelines and new visualization platforms. As well as utilizing and combining the power of other emerging AI methods and capabilities as they evolve.
Can people use Prism AI commercially?
Yes, absolutely. We have a Gaussian Splat commercial license from Volinga who we have been directly collaborating with for a number of months and have been an excellent partner for us. We have already delivered our first commercial projects with some of the fashion industry’s most internationally renowned directors and photographers, I would really LOVE to say more but they are under NDA at this time; they will be visible very soon.
We are also working with a host of early adopting post production companies, such as Lexhag VFX in the UK, for example, who have worked especially closely with us on a full Post Production pipeline for Gaussian Splats with Unreal Engine and other industry recognized compositing tools. So there is a clear and established pipeline all the way to delivery.
How can people get started using Prism AI?
We are holding an industry event at Pinewood Studios, where we are based, for anyone who would like to understand the process deeper, from what we are doing with NeRF and Gaussian Splatting to how they can use that for their own productions. Dates TBC, but any requests for more information should email us directly.
Equally they can email info@prism-ai.io to discuss any projects they would like to capture NeRF or Gaussian Splats for.
What excites you the most about radiance fields?
The potential. I’m a photographer first and foremost, and shooting a radiance field is the first time I have had an opportunity to work where my images can be viewed in real time 360° environments. That brings with it such huge potential for creativity, along with such rapid innovation from technological advancements and AI it’s hard to know where and what we will be working on even in the near future. This is only the beginning and that’s pretty exciting.
Where can people find you?
