Still waiting for the upcoming version of DLSS that probably carries the number “4” and excited to see what sort of technologies will be included for a better gaming experience? NVIDIA’s CEO Jensen Huang’s answer might just signal something.
DSOGaming‘s latest post about the matter talked about Jensen’s comment on the future of DLSS and what he thinks would be part of the “next-gen update”, and here’s a direct quotation from his words.
“We already use AI for neural graphics, and we can generate pixels based off of few input pixels We also generate frame between frames – not interpolation, but generation. In the future, we’ll even generate textures and objects, and the objects can be of lower quality and we can make them look better.”
Focusing on “texture generation,” NVIDIA has been working on this since last year, publicly showcasing the Neural Texture Compression (NTC) solution at Siggraph 2023. The tech reduces the size of texture files while maintaining quality, outperforming formats like AVIF and JPEG XL (allegedly). This innovation could promote mainstream 4K and 8K gaming by reducing VRAM overload and cutting down game storage requirements.
NTC might debut in DLSS 4, though likely as an early implementation that may initially seem unsatisfactory—similar to the original DLSS release. While it holds great potential, it might not yet be ready for full-scale commercial use.
Additionally, NVIDIA’s strategy of reserving the “best and most groundbreaking technologies” for the latest GPU series is nothing new and usually “pisses off” a lot of gamers around the world. However, it would be fair for all RTX cards to benefit from these advancements, not just the “soon-to-be-released” RTX 50 series.
