Adobe filed 1 patent this quarter in Graphics.
The patent covers an AI-powered system that uses machine learning to upscale coarse 3D polygon meshes in real-time, then applies residual data to refine them for high-fidelity rendering. This progressive mesh approach allows for efficient processing of 3D models while maintaining visual quality.
Adobe's single Graphics patent introduces a progressive mesh system designed to speed up 3D rendering without sacrificing final quality. The technology works by first transmitting a simplified, coarse version of a 3D model that gets immediately upscaled using a machine learning model trained specifically on the original mesh dataset. This domain-specific training allows the system to intelligently reconstruct geometry rather than applying generic enlargement techniques. As additional residual correction data arrives over the network, the rendered mesh progressively refines itself to match the full-fidelity original, reducing the amount of data needed for initial display while ensuring the final result remains visually accurate.
All data sourced from USPTO patent filings. Google Patents may take several weeks to index recent publications. If a link is unavailable, search for the patent number at USPTO Patent Public Search.