Last week leading chipmaker Nvidia announced DLSS-5 (Deep Learning Super Sampling), a new artificial intelligence (AI) rendering tool it describes as a “breakthrough in visual fidelity for games”. The software takes low-resolution images and uses AI to upscale them, adding what Nvidia calls “photoreal lighting and materials”.
The tool is designed to make video games look more photorealistic, but the examples Nvidia chose to show off the technology revealed something unexpected: the AI doesn’t just makes images sharper and glossier, it also makes characters significantly more conventionally attractive.
