NVIDIA is preparing to formally announce its new GeForce RTX 50 Series at CES 2025 in a couple of weeks, with the GeForce RTX 5070, RTX 5070 Ti, RTX 5080, and flagship GeForce RTX 5090 set to be unveiled. Multiple leaks from NVIDIA’s partners have confirmed this lineup, and a new leak from INNO3D hints at a revolutionary AI-powered technology coming along with more.

Cyberpunk 2077 is a visually stunning game that makes full use of current GeForce RTX AI technologies, image credit: CD Projekt Red.
VIEW GALLERY – 2 IMAGES
This is our first glimpse at what could be DLSS 4, with the information from INNO3D covering what to expect with the GeForce RTX 50 Series and its AI capabilities for gaming and content creation. According to INNO3D, the GeForce RTX 50 Series will feature Neural Rendering Capabilities, revolutionizing how “graphics are processed and displayed.”
This is in addition to DLSS offering “even better image quality and higher frame rates” and enhanced ray tracing with improved RT cores. It doesn’t stop there, as the next generation of GeForce RTX graphics cards will also be leveraging AI to improve power efficiency and thermal performance when gaming.
Here’s the entire leak.
With the growing importance of AI in gaming and content creation, INNO3D will highlight new AI-accelerated capabilities, giving you the power to Innovate with AI:
- Advanced DLSS Technology: NVIDIA’s Deep Learning Super Sampling offering even better image quality and higher frame rates.
- Enhanced Ray Tracing: Improved RT cores to deliver more realistic lighting, shadows, and reflections in games.
- AI-Accelerated Graphics: Improved performance in AI-assisted tasks and better integration of AI in gaming and content creation workflows.
- Neural Rendering Capabilities: Revolutionising how graphics are processed and displayed.
- AI-Enhanced Power Efficiency: More power-efficient, utilising AI to optimise power consumption and thermal management.
- Improved AI-Driven Upscaling: Beyond gaming, enhanced AI upscaling benefits content creators, offering better quality when scaling up video content.
- Generative AI Acceleration: Optimisations for accelerating generative AI tasks, aligning with the growing trend in AI content creation.
Like other NVIDIA partners, INNO3D is expected to unveil a range of new GeForce RTX Series graphics cards at CES 2025, including new models for its iCHILL and TWIN line-ups. As for what Neural Rendering Capabilities entail, earlier this year, NVIDIA presented a new technology called Real-Time Neural Appearance Models at SIGGRAPH 2024 that dramatically improves the look of in-game objects and materials but also improves shader performance compared to traditional rasterized rendering.
It’s no secret that NVIDIA is all in on AI and has played a significant role in bringing AI to PC gaming with DLSS and Frame Generation, two game-changing bits of technology that have shaped the industry. DLSS 3 debuted with the GeForce RTX 40 Series, so seeing what’s in store this time is exciting. ‘Neural Rendering Capabilities’ is a vague term, but there’s every chance it will be another DLSS moment for the GeForce team.