If you liked DLSS 3.0, you’re going to love DLSS 3.5

The image-enhancing AI gets better—seeing is believing.

August 23, 2023

Jon Peddie

Nvidia’s DLSS 3.5 training has been amplified with a fivefold data increase compared to DLSS 3, enhancing its ability to recognize ray-traced effects and make informed decisions about spatial and temporal data utilization, maintaining high-frequency details for improved upscaling quality. Trained with offline-rendered images, it recognizes complex lighting patterns from training data, re-creating them during gameplay. This surpasses manual denoisers, as seen in Portal with RTX and Cyberpunk 2077 examples. DLSS 3.5’s AI network comprehends diverse scenes, ensuring higher-quality previews before rendering, benefiting applications like D5 Render for architects and designers, available in the fall.(Source: Nvidia)What do we think? Nvidia

...

Enjoy full access with a TechWatch subscription!

TechWatch is the front line of JPR information gathering service, comprising current stories of interest to the graphics industry spanning the core areas of graphics hardware and software, workstations, gaming, and design.

A subscription to TechWatch includes 4 hours of consulting time to be used over the course of the subscription.

Already a subscriber? Login below

If you liked DLSS 3.0, you’re going to love DLSS 3.5

Enjoy full access with a TechWatch subscription!

This content is restricted

Login