Nextech3D.AI Files Patent For Breakthrough Generative AI For 3D-Model Creation

The Company has developed and launched game-changing artificial intelligence (AI) for the $5.5trillion dollar ecommerce industry accelerating the transition from 2D photos to 3D models

TORONTO, ON / ACCESSSWIRE / March 9, 2023 / Nextech3D.AI (formally "Nextech AR Solutions Corp" or the "Company") (OTCQX:NEXCF)(CSE:NTAR)(FSE:EP2), a Generative AI-Powered 3D model supplier for Amazon, P&G, Kohls and other major e-commerce retailers is pleased to announce the Company has filed a provisional patent titled: "Generative AI for 3D Model Creation from 2D Photos using Stable Diffusion with Deformable Template Conditioning." This patent builds on their previous patent filed last year for creating complex 3D models by parts. The game-changing AI technology underpinning these patents places the Company in a leadership position in the 3D modeling for ecommerce space and sets the stage for the Company to become cash flow positive.

Nextech3D.ai CEO Evan Gappelberg comments "We have been preparing for 5-years, anticipating this exact moment in time, where our AI technology would advance far enough to be patentable while simultaneously seeing market demand for photorealistic 3D models for ecommerce pick-up momentum. Today, we now see both the demand side of the 3D model market and the supply side of 3D model production fuelled by ROI and AI, lining up for a breakout year in revenue and cash flow for Nextech3D.ai."

Utilizing recent advances in generative AI, in particular, diffusion models, the invention prescribes a solution for creating 3D models from 2D reference photos, either as a whole, or part-by-part by evolving differentiable, deformable templates to convert into 3D parts, conditioned on one or more reference photos of the part.

Over the years, Nextech has built tens of thousands of high-quality, fully textured, photo-realistic 3D assets, with hundreds of thousands of individual parts. The Company is now harvesting these parts into its part library, synthetically rendering them from random views, and using them to train new diffusion models that are able to reconstruct 3D mesh parts from reference photos. The Company's first clean dataset with 70,000+ 3D objects and more than 2.2M synthetically rendered reference photos are now ready for training. This is still a small portion of all the parts and assets in its model library, and yet, it is already larger than the largest publicly available 3D dataset called ShapeNet, with its 51K models of varying quality. This breakthrough 3D modeling technology positioned the Company to generate significant revenue acceleration and cash flow in 2023 and beyond.