During the Q&A session, Jensen Huang highlighted the key innovation of DLSS 4, which is multi-frame rendering that works on the principle of prediction rather than interpolation as in DLSS 3.
According to Huang, the technology uses previous frames, motion vectors and other data to create new frames with minimal delay. This ensures smoother gameplay and a stable frame rate.
However, new technology requires unique hardware capabilities that are only available in Blackwell architecture.
With DLSS 4, NVIDIA introduced neural textures that reduce the memory space of the materials from, for example, 48 MB to 16 MB. But their implementation depends on the developers, and support for previous generations of video cards is excluded.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
