Newshot
Account

Apex Neural Rendering enters public beta to take on DLSS, works across Nvidia, AMD and Intel GPUs

AI summary

Apex Compute has launched the beta of Apex Neural Rendering (ANR), an AI rendering suite featuring AI frame generation, super resolution and ray reconstruction, which it says supports multiple generations of Nvidia, AMD and Intel GPUs, including some older models, as well as Valve's Steam Deck. The beta runs on Windows 10/11 and Linux, and can run on SteamOS via Proton; only frame generation is available in the beta so far, with the other two features to follow. Apex Compute claims that at 4K on an Nvidia GeForce RTX 5090, ANR generates a frame in 1.01 ms in 2x mode versus 1.26 ms for Nvidia DLSS frame generation, dropping to 0.61 ms and 0.82 ms in 4x mode, and that ANR uses 214 MB of VRAM versus 562 MB for DLSS.

Translation(model translation, not the source's own text)

Challenging DLSS: ANR cross-platform AI rendering technology enters public beta, compatible with NVIDIA, AMD, and Intel graphics cards

IT Home, November 12 news: NVIDIA's DLSS technology has a new competitor. The AI rendering technology suite Apex Neural Rendering (ANR), developed by Apex Compute, has officially launched its beta, including features such as AI frame generation, super resolution, and ray reconstruction.

Unlike NVIDIA DLSS, which is mainly aimed at its own graphics cards, ANR claims compatibility with multiple generations of graphics cards from NVIDIA, AMD, and Intel, and even supports some older models.

Among these, ANR Frame Generation (ANR FG) supports NVIDIA GeForce GTX 16 series and RTX 20 series or newer graphics cards, AMD Radeon RX 5000 series or newer graphics cards, and Intel Arc A series and B series graphics cards. In addition, Valve's Steam Deck handheld is also within the supported range.

On the software side, the currently released beta supports Windows 10/11 and Linux, and can also run on SteamOS through Proton.

According to IT Home, Apex Neural Rendering consists of three technologies: frame generation, super resolution upscaling, and ray reconstruction. However, as of now, only the frame generation feature has entered testing; the other two technologies are expected to be rolled out later.

Apex Compute also published a set of performance data. According to the company's tests, at 4K resolution using an NVIDIA GeForce RTX 5090 graphics card, ANR takes only 1.01 milliseconds to generate a frame in 2x mode, while NVIDIA DLSS frame generation takes 1.26 milliseconds. In 4x mode, the times drop to 0.61 milliseconds and 0.82 milliseconds, respectively.

In terms of VRAM usage, ANR is said to require only 214 MB, while DLSS requires 562 MB.

If these figures are accurate, ANR could potentially address one of the main pain points of frame generation technology: the additional latency. Although frame generation can increase the displayed frame rate, the processing itself may also introduce extra latency, affecting input responsiveness.

In addition to performance and VRAM usage, Apex Compute also claims that ANR can provide better image quality and has published multiple image comparison sets, including game scenes from The Last of Us Part II.

However, these figures and image comparisons all come from the developer itself and cannot yet serve as evidence that ANR comprehensively surpasses DLSS. The final performance still requires independent testing, especially verification in actual game environments. After all, faster frame generation does not necessarily mean better overall game performance, nor does it necessarily reduce the input latency actually felt by players.

The ANR FG beta is now available for download on GitHub, and at this stage it relies on the OptiScaler tool to run. The installation process requires modifying each game's individual directory, and is not as simple as adjusting a few sliders in the game settings. Therefore, compatibility may vary considerably from game to game.

For players who want to experience AI frame generation technology on graphics cards from different brands, ANR offers a new option. However, whether it can truly become a strong competitor to DLSS still depends on the later implementation of the other two technologies and more independent test results.

Related articles

  • NVIDIA App 11.0.9.585 released: DLSS optimizations added for 19 games including PUBG: BATTLEGROUNDS
  • Beating Where Winds Meet to the punch, NetEase's Naraka: Bladepoint officially supports NVIDIA DLSS 5 technology, becoming the first domestic game to implement it
  • First in China: NetEase's Where Winds Meet officially announces implementation of NVIDIA DLSS 5 on November 24
  • Hogwarts Legacy to support NVIDIA DLSS 5 starting the day after tomorrow, with War Thunder, Where Winds Meet, and other games to follow
  • Mario Kart World with NVIDIA DLSS 5, with image quality comparable to an animated film
  • Report says Nintendo's The Legend of Zelda: Ocarina of Time remake uses FSR 1.0 super resolution and does not support NVIDIA DLSS

The translation is machine-generated and individual terms may be off. Nothing is rewritten or cut; the original is authoritative.

Published by IT之家
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗