NVIDIA Introduces DLSS 5 with 3D-Guided Neural Rendering, Expands ACE Tools, and Updates RTX Kit

NVIDIA Introduces DLSS 5 with 3D-Guided Neural Rendering, Expands ACE Tools, and Updates RTX Kit NVIDIA has unveiled DLSS 5, introducing a 3D-guided neural rendering stage alongside developer controls, while also releasing updates across the NVIDIA ACE character AI suite and the RTX Kit SDK. DLSS 5 operates as a deterministic, one-frame-in, one-frame-out neural stage running at up to 4K on a single GeForce RTX 50 Series GPU, premiering in NBA 2K27. NVIDIA ACE adds Nemotron Speech 3.5 Streaming and Qwen3 TTS, alongside In-Game Inference SDK updates supporting RTX Spark preview, Gemma4, and Stable Diffusion plugins. RTX Kit 2026.3 updates character rendering, neural textures, neural shading, and dynamic illumination with DLSS Ray Reconstruction. RTX Mega Geometry 2.0 introduces continuous level-of-detail cluster streaming for high-density meshes and is set to appear in Gears of War: E-Day. DLSS 5 and 3D-Guided Neural Rendering DLSS 5 acts as a final neural-rendering phase that takes the game engine's rendered frame—including geometry, textures, and lighting buffers—as a foundation. Designed for real-time 3D, the model uses frame color and engine motion vectors to ensure temporal stability while running locally at up to 4K on GeForce RTX 50 Series GPUs. Developers can fine-tune art direction through model selection, Structure Intensity, Tone Intensity, and AI or engine-level masking. In NBA 2K27 by Visual Concepts, DLSS 5 enhances skin subsurface scattering, hair lighting, and contact shadows while preserving scanned player likenesses. NVIDIA ACE and In-Game Inferencing NVIDIA ACE expands its character-building pipeline with Nemotron Speech 3.5 Streaming (a 600M-parameter ASR model) and Qwen3 TTS (a 600M-parameter TTS model supporting custom fine-tuning). The NVIDIA In-Game Inferencing (NVIGI) SDK adds developer preview support for the RTX Spark platform for slim laptops and compact desktops, integrates Gemma4 into its GPT plugin, adds a Stable Diffusion plugin, and incorporates upstream llama.cpp performance enhancements. RTX Kit 2026.3 and RTX Mega Geometry 2.0 RTX Kit 2026.3 brings DLSS Ray Reconstruction integration to RTX Dynamic Illumination 3.1, refines BCSDF hair sampling in RTX Character Rendering 1.4, and introduces Collaborative Texture Filtering 1.3. RTX Neural Texture Compression 0.10 beta and RTX Neural Shading 1.4 add compatibility with the DirectX 12 Agility SDK preview featuring Linear Algebra, with both neural textures and texture filtering gaining Windows ARM64 support. In parallel, RTX Mega Geometry 2.0 introduces streaming for continuous level-of-detail clusters on high-density meshes, which will be integrated alongside DLSS into Gears of War: E-Day.

英伟达面向游戏开发者推出DLSS 5、ACE更新及RTX Kit新功能 英伟达发布了一系列针对游戏开发者的技术更新，包括引入3D引导神经渲染的DLSS 5、扩展角色AI与本地推理的NVIDIA ACE，以及包含RTX Mega Geometry 2.0在内的RTX Kit工具套件升级。 DLSS 5引入3D引导神经渲染，以引擎渲染帧为基础添加真实材质与光照，并已在《NBA 2K27》中上线。 NVIDIA ACE新增Nemotron Speech 3.5 Streaming与Qwen3 TTS模型，本地推理SDK支持RTX Spark预览版与Gemma4等模型。 RTX Kit 2026.3更新了神经纹理压缩、动态照明等组件，并推出支持连续细节级别簇流式传输的RTX Mega Geometry 2.0。 DLSS 5与3D引导神经渲染 DLSS 5将图形管线扩展为最终的神经渲染阶段，以游戏引擎生成的几何体、纹理和光照缓冲区为基础，结合帧颜色与运动矢量增添真实光照与材质细节，同时保持场景结构与艺术意图。该模型采用单帧输入输出机制，可在单块GeForce RTX 50系列GPU上以最高4K分辨率本地运行。开发者可通过结构强度、色调强度调节细节，并结合语义AI掩码和引擎掩码精细控制效果。该技术已落地于《NBA 2K27》，支持RTX 50系列桌面、笔记本GPU及GeForce NOW Ultimate云端串流。 NVIDIA ACE模型与本地推理框架更新 NVIDIA ACE扩展了语音管线，引入了6亿参数的流式语音识别模型Nemotron Speech 3.5 Streaming，以及同样为6亿参数、支持自定义微调的高质量文本转语音模型Qwen3 TTS。游戏内推理SDK（NVIGI）支持通过C++在进程内本地运行AI模型，最新更新加入了针对轻薄本和高效台式机平台RTX Spark的开发者预览支持，将Gemma4整合至GPT插件，并新增Stable Diffusion插件与最新llama.cpp性能优化。 RTX Kit 2026.3与RTX Mega Geometry 2.0 RTX Kit 2026.3升级了多个渲染组件，包括支持DLSS光线重建的RTX Dynamic Illumination 3.1、支持DirectX 12 Agility SDK预览版与Windows ARM64的神经纹理压缩0.10 beta，以及提升随机纹理放大质量的RTX Texture Filtering 1.3。此外，RTX Mega Geometry SDK升级至2.0，支持高密度网格的连续细节级别（LOD）簇流式传输，该技术即将应用于《战争机器：E-Day》（Gears of War: E-Day）。

[NVIDIA DLSS 5](https://www.nvidia.com/en-us/geforce/news/dlss-5-3d-guided-neural-rendering/) introduces DLSS 3D-Guided Neural Rendering and granular controls that help game developers add lifelike lighting and material detail while preserving their artistic intent. We also look at updates to [NVIDIA ACE](https://developer.nvidia.com/ace-for-games), RTX Mega Geometry 2.0, and RTX Kit across character AI, high-density geometry, and rendering workflows. This post covers: - How DLSS 5 uses the game engine’s rendered frame as the foundation for 3D-Guided Neural Rendering and how NBA 2K27’s developer, Visual Concepts, uses DLSS 5 to enhance materials and lighting while preserving scanned facial geometry - New NVIDIA ACE speech and inferencing capabilities - RTX Kit SDK updates including RTX Mega Geometry 2.0 support for streaming continuous level-of-detail clusters ## DLSS 5 introduces 3D-guided neural rendering with developer controls DLSS 5 with 3D-guided neural rendering extends the graphics pipeline as a final neural-rendering stage. It uses the game engine’s rendered frame, including its artist-authored geometry, textures, and lighting buffers as an unyielding foundation. The engine frame defines what must remain, while developers direct what may change. Using frame color and motion vectors, the model is designed to add lifelike lighting and material detail while preserving scene structure, character identity, and artistic intent. Built specifically for real-time 3D rendering, DLSS 5 delivers deterministic, temporally stable output. Operating on a strict one-frame-in, one-frame-out model with game-engine motion vectors keeps results consistent as players move. The compact, specialized model runs locally on a single GeForce RTX 50 Series GPU at up to 4K. **Controls and integration for developers** - **Art direction:** Developers can choose from among several models, mix them across scenes, gameplay, or cutscenes, and adjust Structure Intensity and Tone Intensity to tune high-frequency detail and broader lighting and color response. - **Targeted application:** Developers can use semantic AI masking to apply or hold back the effect across recognized scene elements, then use engine-level masks to isolate props or asset groups such as glassware, water droplets, and foliage. - **Input quality:** DLSS 5 noticeably elevates traditional rasterized graphics, but giving the model richer source data, like ray-traced or path-traced lighting, yields dramatically more-accurate results. DLSS 5 is available now in NBA 2K27, developed by Visual Concepts and published by 2K, for all GeForce RTX 50 Series desktop and laptop GPUs. GeForce NOW Ultimate members can also experience it when streaming from NVIDIA-operated GeForce RTX 5080-powered gaming rigs in the cloud. Visual Concepts uses overall tone and style controls plus a per-pixel uplift control mask to fine-tune character detail while respecting player likenesses. In *NBA 2K27*, DLSS 5 preserves scanned facial geometry while enhancing skin subsurface scattering, light transmission through hair and ears, and contact shadows. For more details about DLSS 5, check out our [DLSS 5 article](https://www.nvidia.com/en-us/geforce/news/dlss-5-3d-guided-neural-rendering/). Sign up to be notified for DLSS updates for developers [here](https://developer.nvidia.com/rtx/dlss/notify-me). ## NVIDIA ACE expands model and platform support NVIDIA ACE offers ready-to-integrate AI models and tools for building knowledgeable, interactive, and conversational in-game characters. The latest updates expand the speech pipeline and inference framework, making it easier for developers to run AI in their games. To run these models locally alongside game graphics, the NVIDIA In-Game Inferencing (NVIGI) SDK delivers a high-performance, streamlined path for deploying local AI models through in-process C++ execution. **Key Release Highlights** - [**NVIDIA Nemotron Speech 3.5 Streaming**](https://developer.nvidia.com/ace-for-games): A 600M-parameter Automatic Speech Recognition (ASR) model that transcribes player speech using a streaming architecture designed to minimize latency while maintaining accuracy. - [**Qwen3 TTS**](https://developer.nvidia.com/ace-for-games): A 600M-parameter Text-to-Speech model that generates high-quality audio and supports custom fine-tuning. **NVIDIA In-Game Inference SDK Updates** - **RTX Spark Support (Developer Preview)**: Adds early support for RTX Spark, NVIDIA’s new AI and graphics platform for slim laptops and ultra-efficient desktops. - **Expanded Model Support**: Integrates Gemma4 into the GPT plugin. - **New Plugins & Samples**: Adds a Stable Diffusion plugin along with sample code. - **Performance Enhancements**: Incorporates the latest `llama.cpp` updates to maximize inference performance. Access NVIDIA In-Game Inference SDK [here](https://developer.nvidia.com/rtx/in-game-inferencing). ## Updates across NVIDIA RTX Kit advance neural rendering and path tracing NVIDIA RTX Kit is a suite of rendering technologies for training and deploying AI in shaders, path tracing detailed scenes at game-ready performance, and rendering lifelike digital characters. The latest SDK updates expand support for high-density geometry, neural texture workflows, lighting, and texture filtering. RTX Kit 2026.3 updates include: - RTX Character Rendering 1.4 improves far-field hair BCSDF sampling and energy conservation - RTX Dynamic Illumination 3.1 adds DLSS Ray Reconstruction integration and some improvements to ReSTIR PT - RTX Neural Texture Compression 0.10 beta adds support for the Microsoft DirectX 12 Agility SDK preview with Linear Algebra, enabling RTX Tensor Core acceleration for neural texture decompression in DirectX shaders. It also adds Windows ARM64 support. - RTX Neural Shading 1.4 adds support for the latest DirectX Linear Algebra preview toolchain and updates its shader and sample dependencies. - RTX Texture Filtering 1.3 introduces Collaborative Texture Filtering, a technique designed to improve magnification quality for stochastic texture filtering. It also adds Windows ARM64 support. ### RTX Mega Geometry 2.0 is now available In addition to the RTX Kit updates, [RTX Mega Geometry SDK](https://github.com/NVIDIA-RTX/RTXMG) has been updated to 2.0 which adds support for streaming of continuous level-of-detail clusters for high-density meshes. The scale of detail is demonstrated in a newly released textured glTF version of Zorah. RTX Mega Geometry is coming soon to Gears of War: E-Day, offering GeForce games higher frame rates, higher levels of image quality, and with even more responsive controls. We sat down with the Coalition’s Studio Technical Director, Kate Rayner, and Rendering Lead, Mike Perzel to learn more about Gears of War: E-Day’s integrations of RTX Mega Geometry and DLSS. *Video 3. RTX: Inside the Game | Gears of War: E-Day with DLSS 4.5 and RTX Mega Geometry* ## Resources for game developers Check out the full list of [game developer resources](https://developer.nvidia.com/game-development) and stay up to date with the latest NVIDIA game development news: - Subscribe to our [newsletter](https://developer.nvidia.com/email-signup) (select gaming as your industry) - Follow us on social: [X](https://x.com/NVIDIAGameDev), [LinkedIn](https://www.linkedin.com/showcase/79124990/), [Facebook](https://www.facebook.com/NVIDIAGameDev/), and [YouTube](https://www.youtube.com/@NVIDIAGameDeveloper/featured) - Join our [Discord community](https://discord.com/invite/C8FKNVMnhq)