Apex Neural Rendering frame generation, Digi Mart USA News: Apex Compute has introduced Apex Neural Rendering (ANR), a suite of AI-powered rendering technologies that the company says can compete with Nvidia DLSS. The suite is designed to work across graphics cards from Nvidia, AMD and Intel, including some fairly old models.
ANR Frame Generation, the only component currently available in beta, supports Nvidia GeForce GTX 16-series and RTX 20-series GPUs or newer, AMD Radeon RX 5000-series GPUs or newer, and Intel Arc A-series and B-series graphics cards. The Steam Deck is also supported.
The beta runs on Windows 10 and 11, Linux, and SteamOS through Proton.
Apex Neural Rendering consists of three technologies: frame generation, super-resolution upscaling and ray reconstruction. Apex Compute says the other two components are expected to arrive later, but they are not yet available in beta.
The company has published performance figures for a GeForce RTX 5090 at 4K. ANR reportedly takes 1.01 milliseconds to generate a frame in 2x mode, compared with 1.26 milliseconds for Nvidia DLSS Frame Generation.
In 4x mode, the figures are 0.61 and 0.82 milliseconds respectively. ANR also reportedly uses 214 MB of GPU memory, compared with 562 MB for DLSS.
These are first-party claims, and independent testing will be needed to confirm them.
Apex Compute also says its solution produces better image quality and has published side-by-side comparisons, including scenes from The Last of Us Part II. Faster frame generation alone does not necessarily translate into better overall performance or lower input latency in real games.
The ANR FG beta is available on GitHub and currently relies on OptiScaler. Installation requires modifying individual game directories rather than simply adjusting in-game settings, so compatibility is expected to vary between games.
