Shutterstock joins others in making NeRF Generative AI Technology accessible to 3D creators around the world
Shutterstock, Inc, a leading global creative platform providing high-quality content and full-service creative workflow solutions for innovative brands, digital media and marketing companies, an announced its intention to enter into three separate collaboration agreements with Luma Labs AI, RECON Labs and Volinga AI leading startup innovators in the field of new Neural Radiance Fields technology. The companies announced their respective plans at this year’s SIGGRAPH 2023, the 50th Annual International Conference and Exhibition for Computer Graphics and Interactive Technologies.
“We’re very excited to expand our research and development efforts into this next phase of 3D AI technology, in collaboration with some of the most innovative and forward-thinking minds in creative production,” commented Dade Orgeron, vice president of innovation at Shutterstock /Turbosquid, “In driving awareness and adoption of NeRF technology, it is critical for us to partner with innovators who share our commitment to developing creative technologies that enhance the creative process while protecting and repaying our artist community.”
Using 3Dpresso from Luma and RECON Labs, Shutterstock aims to explore the rapidly evolving field of NeRF technology using Shutterstock’s extensive 2D/3D asset database and add both companies’ existing 3D assets to Shutterstock’s Turbosquid platform for commercial licensing .
“3D is a powerful creative medium that will be a leading format for the stories of the future, which is why we founded Luma in 2021. We’re on a mission to democratize 3D and make Hollywood-quality photorealistic 3D accessible to everyone. High quality and lifelike real-time 3D scenes are now a reality for anyone using Luma, whether on the web or in the Unreal Engine with the new .luma scenes,” said Amit Jain , co-founder and CEO of Luma. “As a global leader in NeRF research and products, we are excited to partner with Shutterstock and bring Luma’s world-class generative 3D platform to Shutterstock creatives. This will bring this incredible 3D technology to every artist, studio and mobile sooner than ever!”
Traditionally, creating 3D scenes took several hours, depending on the desired complexity and resolution for the desired landscape or environment. With the advent of NeRF technology, developed using advanced machine learning and computer vision, 3D developers can produce high-resolution, photorealistic 3D scenes from 2D video in minutes.
“NeRF technology gives the Shutterstock community the opportunity to help build the world’s largest library of NeRF-based content, from entire environments to individual objects from around the world,” said Orgeron. how we create 3D content because it builds on the tool that photographers and video are already familiar with: cameras.”
Shutterstock has also entered into an agreement with Volinga AI to explore licensing and distribution opportunities for NVOL files. Volinga offers a comprehensive range of NeRF-related products and services through its professional NeRF Suite to support virtual production, VFX, TV and broadcast, XR and video games. As part of the agreement, Shutterstock and Volinga also plan to create an NVOL library of high-quality content for Volinga users and the first network of creators to produce on-demand NVOL environments.
This Volinga network would complement Shutterstock’s existing network of more than two million artists and creators around the world who contribute to Shutterstock’s library of ethical, licensable 2D, 3D, video and audio content. To date, Shutterstock, through its Contributor Fund, has compensated hundreds of thousands of artists for the role their intellectual property played in shaping Shutterstock’s generative technology, and has paid artists ongoing royalties on newly generated content tied to the licensing activities.
“We are committed to unlocking the full potential of NeRF and making this breakthrough technology accessible to professionals,” said Fernando Rivas-Manzaneque, co-founder of Volinga AI. “This library of production-ready NVOL assets will enable our users to to immediately start experimenting and using NeRF in their volumes, lowering the barrier to entry for this technology. Moreover, the network of creatives producing on-demand NVOL environments that we are striving to achieve with Shutterstock, virtual production will definitely take it to the next level.”
As part of the new TurboSquid Labs, where Shutterstock will release the first example of its Virtual Locations product a complete, production-ready NeRF environment – the company will also work closely with Luma, Volinga and RECON Labs, among other innovators in the NeRF space and generative AI will work together to develop a specification and best practice standard for capturing high quality NeRFs.
In March, Shutterstock also announced its collaboration with NVIDIA to develop AI base models for tools for 3D generative artists. As part of this collaboration, Generative AI models will be trained with Shutterstock assets using NVIDIA Picasso’s Generative AI cloud services to rapidly convert text prompts into faithful 3D content for industrial digital twins, entertainment and gaming.
These announcements follow several strategic steps Shutterstock has taken as a leading innovator to bring ethical and responsible AI advancements to the creative industries. Shutterstock also recently joined the Content Authenticity Initiative, whereby the company will support the CAI’s goal of combating the spread of misleading information online by implementing technical standards to certify the source and history of media content through the integration of content attribution. Shutterstock intends to integrate the underlying Coalition for Content Provenance and Authenticity into its AI capabilities and various creativity tools, including the DALL·E-powered one AI Image Generator and suite of AI-powered applications to further protect its users with verifiable and tamper-proof information about all types of content. Among other things, content credentials ensure that each asset is certified with secure metadata about its creation, authorship and editing history.
SOURCE : PRNewswire
Comments are closed.