# NVIDIA Unveils DLSS 5 with 3D-Guided Neural Rendering and ACE Updates New developer tools enhance real-time graphics and in-game AI capabilities - **Source:** [Nvidia Developer Blog](https://developer.nvidia.com/blog) - **Published:** 2026-09-22 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/7808c343-3ff8-418e-9005-0e42ac7098a5 ## DLSS 5 Core Innovation NVIDIA's DLSS 5 introduces 3D-Guided Neural Rendering that uses game engine frames as foundation, adding lifelike lighting while preserving artistic intent. The technology operates on a strict one-frame-in, one-frame-out model with game-engine motion vectors for stable output. It runs locally on GeForce RTX 50 Series GPUs at up to 4K resolution, maintaining temporal stability as players move through game environments. ## Developer Control Features DLSS 5 provides granular controls including model selection, Structure Intensity and Tone Intensity adjustments. Developers gain semantic AI masking and engine-level masking capabilities to direct neural rendering effects. These tools allow precise control over how AI enhances different scene elements while respecting original artistic vision. The system is already implemented in NBA 2K27 for RTX 50 Series GPUs. ## Character Rendering Advancements In NBA 2K27, DLSS 5 preserves scanned facial geometry while enhancing skin subsurface scattering and light transmission through hair. Visual Concepts uses per-pixel uplift control masks to fine-tune character details while maintaining player likenesses. The technology improves contact shadows and material details without compromising the original character models. ## ACE AI Character Updates NVIDIA ACE expands with Nemotron Speech 3.5 Streaming for low-latency speech recognition and Qwen3 TTS for high-quality text-to-speech. The platform offers ready-to-integrate AI models for building interactive in-game characters. Developers can now access improved speech pipelines and inference frameworks for more natural character interactions. ## In-Game AI Deployment The NVIDIA In-Game Inferencing SDK adds RTX Spark support and Gemma4 integration for local AI deployment. New features include Stable Diffusion plugin and llama.cpp performance enhancements. This provides a unified plugin architecture for running AI models alongside graphics workloads within game processes. ## RTX Mega Geometry 2.0 Updated RTX Mega Geometry SDK adds streaming of continuous level-of-detail clusters for high-density meshes. Demonstrated with a textured glTF version of Zorah, the technology organizes detailed meshes into adaptive clusters. This enables efficient ray-traced scenes that maintain high geometric detail without performance penalties. ## Game Integration Timeline RTX Mega Geometry is coming soon to Gears of War: E-Day, promising higher frame rates and image quality. The Coalition's technical team has integrated both Mega Geometry and DLSS technologies. These implementations will offer more responsive controls alongside visual enhancements in the upcoming title. ## Developer Ecosystem Impact NVIDIA's 2026.3 updates represent significant advancements for real-time rendering pipelines. The combination of neural rendering, path tracing, and AI character systems creates new possibilities for game developers. These technologies collectively push boundaries in visual fidelity while maintaining performance requirements for modern gaming experiences. ## Sources covering this story - https://developer.nvidia.com/blog/whats-new-for-game-developers-dlss-5-with-3d-guided-neural-rendering-nvidia-ace-updates-and-new-rtx-kit-capabilities/ — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._