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

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