Arm Releases Neural Super Sampling for Next-Gen AI Upscaling in Gaming

Neural Super Sampling (NSS), a next-generation AI-powered upscaling solution from Arm, has been released for graphics and gaming developers to start experimenting today. This technology enables high-resolution rendering at a lower compute cost by reconstructing high-quality output frames from low-resolution temporal inputs.

What Happened

Arm announced the release of NSS on August 12, 2025, as part of its neural technology that will ship in Arm GPUs in 2026. The first use case of this technology is Neural Super Sampling (NSS), a next-generation AI-powered upscaling solution designed for real-time performance on future mobile devices with Arm Neural Technology.

The NSS model has been integrated into Unreal Engine via two plugins, the NSS Plugin for Unreal and the Unreal NNE Plugin for ML extensions for Vulkan. These plugins enable developers to start experimenting with NSS today. The current version of the dataset includes a limited set of data for Neural Super Sampling to demonstrate how the NSS model development flow works.

Background and Context

Temporal super sampling (TSS), also known as TAA, has become an industry standard solution for anti-aliasing over the last decade. However, it is not without its challenges. Hand-tuned heuristics, commonly used in TSS approaches today, can be difficult to scale and require continual adjustment across varied content.

NSS overcomes these limitations by using a trained neural model that learns from data. It generalizes across conditions and content types, adapting to motion dynamics and identifying aliasing patterns more effectively. This capability helps NSS handle edge cases more reliably than approaches such as AMD's FSR 2 and Arm ASR.

The training process for the NSS network involves recurrent learning with feedback. The model is trained using sequences of 540p frames rendered at 1 sample per pixel, paired with 1080p ground truth images rendered at 16spp. Inputs include rendered images, such as color, motion vectors, and depth, alongside engine metadata, such as jitter vectors, and camera matrices.

Why it Matters to the Industry

The release of NSS has significant implications for the adult industry, particularly in terms of latency, scale, and moderation. With the ability to render high-resolution content at a lower compute cost, platforms can improve user experience while reducing costs associated with hardware upgrades.

NSS also enables more efficient use of bandwidth, which is critical for live streaming and real-time video conferencing applications prevalent in the adult industry. Furthermore, the technology's adaptability to motion dynamics and aliasing patterns makes it an attractive solution for handling edge cases that often plague traditional upscaling methods.

What Comes Next

The release of NSS marks a significant step forward in the development of AI-powered upscaling solutions. As Arm continues to refine and improve the technology, we can expect to see increased adoption across various industries, including the adult sector.

Arm has made available several resources for developers looking to integrate NSS into their projects, including technical blogs, white papers, and a GitHub repository containing plugins for Unreal Engine. These resources provide a comprehensive guide for developers to get started with NSS and explore its capabilities in more detail.

Key Facts

• NSS is a next-generation AI-powered upscaling solution from Arm designed for real-time performance on future mobile devices with Arm Neural Technology.
• The NSS model has been integrated into Unreal Engine via two plugins, the NSS Plugin for Unreal and the Unreal NNE Plugin for ML extensions for Vulkan.
• NSS overcomes limitations of traditional upscaling methods by using a trained neural model that learns from data and generalizes across conditions and content types.
• The training process for the NSS network involves recurrent learning with feedback, using sequences of 540p frames rendered at 1 sample per pixel paired with 1080p ground truth images rendered at 16spp.
• NSS has significant implications for the adult industry in terms of latency, scale, and moderation, enabling more efficient use of bandwidth and handling edge cases more reliably than traditional upscaling methods.