Arm Details Its Mobile‑First AI Reconstruction Approach, Offering an Alternative to the Closed‑Box DLSS 5 Model

Arm, the British semiconductor and software design powerhouse, recently hosted its Arm Everywhere China showcase in Shanghai, unveiling a suite of new AI‑driven technologies aimed at reshaping mobile graphics. The centerpiece of the announcement is the AI‑native compute platform CSS for Mobile 2 and the Mali G2‑Ultra NX GPU, a processor built around neural acceleration that promises higher visual fidelity while keeping power draw and heat generation low. Arm positions its on‑device AI solution as a more open, developer‑friendly alternative to Nvidia’s contentious DLSS 5, arguing that its method stays truer to the original artistic intent of game creators. While Arm did not name specific products that will ship with the Mali G2‑Ultra NX, the predecessor Mali G1‑Ultra is already found in smartphones from manufacturers such as Xiaomi, Vivo, and OnePlus, suggesting a similar market trajectory.

Deyan Lazarov, a member of Arm’s GPU product team within the Edge AI division, explained that the new chip has been in development for roughly two and a half years. Its primary goal is to give mobile developers the ability to harness compute‑heavy features—most notably ray tracing—without the traditional penalties of heat and battery drain. "We’ve seen a steady rise in mobile titles experimenting with ray tracing," Lazarov noted.

"It took a while to gain momentum, but now more developers are actively looking to incorporate it into their games." The Mali G2‑Ultra NX is designed to support Unreal Engine capabilities such as MegaLights, and Arm has already partnered with Sumo Digital to produce a demo title, Neural Dawn, that showcases the chip’s capabilities. Lazarov described the target audience as "mobile‑first games that still want to look like desktop experiences," as well as cross‑platform titles that aim to deliver a consistent visual quality across consoles, PCs, and phones. He emphasized that gamers should not notice a dramatic drop in fidelity when moving from a home console to a train‑riding session on a smartphone. Several upcoming games will leverage the new GPU, including Tencent’s Arena Breakout Infinite, NetEase’s Where Winds Meet, and Infold Games’ Infinity Nikki.

However, Lazarov reminded listeners that phones operate under very different thermal and power constraints than consoles or PCs. "A phone can’t dissipate heat the way a console can, and it’s always running on a battery," he said. To address these constraints, Arm integrates neural processing directly into the traditional rendering pipeline. By offloading portions of the workload to dedicated neuro‑accelerators, the GPU’s power consumption drops, which in turn improves overall system efficiency.

"This new efficiency removes many of the trade‑offs developers usually have to make," Lazarov explained. "They can choose to reinvest the saved budget into higher visual fidelity, smoother performance, longer battery life, or a mix of all three." Arm’s strategy for encouraging adoption hinges on openness.

Over the past two years the company has been collaborating with the broader ecosystem to create a suite of tools that are developer‑centric. The AI‑enhanced graphics stack includes Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD), and Neural Frame‑Rate Upscaling (NFRU).

These technologies can upscale images, add extra rays, and generate additional frames using AI reconstruction. Lazarov illustrated the process with a two‑frame example. In the first frame, the GPU renders only 25 % of the image while the neuro‑accelerators reconstruct the remaining three quarters using NSS. In the second frame, the GPU does no traditional rendering at all; every pixel is produced by the neural engine, resulting in a fully AI‑reconstructed frame.

Nvidia’s DLSS 5 also uses AI to enhance image detail, but it has drawn criticism for its “black‑box” nature, which can sometimes stray from a developer’s artistic vision. Arm draws a clear distinction: "Our networks are not generative; they are convolutional, meaning they don’t invent new content, they simply know how existing content should look. We train them on real data and make the models publicly available on GitHub and Hugging Face." This openness lets developers fine‑tune the models for their own artistic styles. If a game has a unique visual language, developers can capture datasets from their own title, retrain Arm’s public networks, and ensure that upscaling and frame generation respect the game’s distinctive look.

"There’s no risk of losing IP control," Lazarov emphasized, contrasting this with Nvidia’s proprietary, opaque approach where developers must accept the model as‑is or abandon it. Another key differentiator is the mobile‑first design philosophy.

Arm’s networks are built with strict power, bandwidth, and memory budgets in mind. "DLSS would simply exceed a phone’s limits even if the software were supported," Lazarov said.

"Our solution fits within the tight constraints of mobile hardware." Power efficiency is a major selling point. Arm reports up to a four‑fold increase in performance and efficiency, along with a 70 % reduction in DRAM traffic—a major source of power consumption on handheld devices. Less external memory access translates directly into longer battery life. In practical terms, the performance uplift is dramatic.

When pushing the previous‑generation GPU to its limit, Neural Dawn could only achieve 40 fps under ideal conditions and dropped to 15 fps in typical usage. The Mali G2‑Ultra NX runs the same title smoothly at 60 fps.

From a developer tooling perspective, Arm currently offers plugins for Unreal Engine and plans to expand to other engines, with Unity support on the roadmap. A recent partnership with Unity China signals that Unity integration is forthcoming.

For studios using custom engines, Arm provides an SDK that streamlines integration without requiring bespoke plugins. Lazarov highlighted that existing games can be upgraded relatively quickly. "If you have a shipped title and want to integrate our AI‑native graphics, you could be ready to release an updated version in as little as three months." The demo Neural Dawn was built by a team of fewer than 20 people in under 18 months, demonstrating how Arm’s technology can accelerate development cycles and enable smaller teams to deliver high‑quality experiences.

In summary, Arm’s Mali G2‑Ultra NX and accompanying AI‑native graphics stack aim to give mobile developers a powerful, open, and efficient alternative to closed‑source solutions like DLSS 5. By embedding neural acceleration into the rendering pipeline, providing publicly available models for customization, and designing everything around mobile constraints, Arm hopes to empower creators to push visual boundaries without sacrificing battery life or thermal headroom.