Info Zone - gEngines, Ray Tracing, AI, DLSS, DLAA, DLDSR, TSR, FSR, XeSS, DirectSR and MODS etc.

same way i came to the conclusion you have no idea about lighting passes.

 

RT 3.0 & DLSS 3.0

 

https://videocardz.com/press-releas...lss-3-upscaling-technology-35-games-on-a-list
Introducing NVIDIA DLSS 3 – A Revolution in Neural Graphics
DLSS 3 is a revolutionary breakthrough in AI-powered graphics that massively boosts performance, while maintaining great image quality and responsiveness. Building upon DLSS Super Resolution, DLSS 3 adds Optical Multi Frame Generation to generate entirely new frames, and integrates NVIDIA Reflex low latency technology for optimal responsiveness. DLSS 3 is powered by the new fourth-generation Tensor Cores and Optical Flow Accelerator of the NVIDIA Ada Lovelace architecture, which powers GeForce RTX 40 Series graphics cards.

The DLSS Frame Generation convolutional autoencoder takes 4 inputs – current and prior game frames, an optical flow field generated by Ada’s Optical Flow Accelerator, and game engine data such as motion vectors and depth.



Ada’s Optical Flow Accelerator analyzes two sequential in-game frames and calculates an optical flow field. The optical flow field captures the direction and speed at which pixels are moving from frame 1 to frame 2. The Optical Flow Accelerator is able to capture pixel-level information such as particles, reflections, shadows, and lighting, which are not included in game engine motion vector calculations. In the motorcycle example below, the motion flow of the motorcyclist accurately represents that the shadow stays in roughly the same place on the screen with respect to their bike.

Whereas the Optical Flow Accelerator accurately tracks pixel level effects such as reflections, DLSS 3 also uses game engine motion vectors to precisely track the movement of geometry in the scene. In the example below, game motion vectors accurately track the movement of the road moving past the motorcyclist, but not their shadow. Generating frames using engine motion vectors alone would result in visual anomalies like stuttering on the shadow.

For each pixel, the DLSS Frame Generation AI network decides how to use information from the game motion vectors, the optical flow field, and the sequential game frames to create intermediate frames. By using both engine motion vectors and optical flow to track motion, the DLSS Frame Generation network is able to accurately reconstruct both geometry and effects, as seen in the picture below.

 

DLSS 3 technology will only work on Ada Lovelace architecture graphics cards, RTX 2000 and RTX 3000 graphics cards will not support DLSS 3 technology.

 

OP Updated: DLSS3 games

Spoiler: More

• A Plague Tale: Requiem
• Atomic Heart
• Black Myth: Wukong
• Bright Memory: Infinite
• Chernobylite
• Conqueror’s Blade
• Cyberpunk 2077
• Dakar Rally
• Deliver Us Mars
• Destroy All Humans! 2 – Reprobed
• Dying Light 2 Stay Human
• F1Ⓡ 22
• F.I.S.T.: Forged In Shadow Torch
• Frostbite Engine
• HITMAN 3
• Hogwarts Legacy
• ICARUS
• Jurassic World Evolution 2
• Justice
• Loopmancer
• Marauders
• Microsoft Flight Simulator
• Midnight Ghost Hunt
• Mount & Blade II: Bannerlord
• Naraka: Bladepoint
• NVIDIA Omniverse
• NVIDIA Racer RTX
• PERISH
• Portal with RTX
• Ripout
• S.T.A.L.K.E.R. 2: Heart of Chornobyl
• Scathe
• Sword and Fairy 7
• SYNCED
• The Lord of the Rings: Gollum
• The Witcher 3: Wild Hunt
• THRONE AND LIBERTY
• Tower of Fantasy
• Unity
• Unreal Engine 4 & 5
• Warhammer 40,000: Darktide

 

https://www.nvidia.com/en-gb/geforce/news/dlss3-ai-powered-neural-graphics-innovations/

 

Cyberpunk 2077 will get a Ray Tracing Overdrive Mode

NVIDIA and CD Projekt RED have announced that a new free update for Cyberpunk 2077 will add support for a new Ray Tracing mode, called Overdrive Mode. In addition, this upcoming patch will add support for the next version of DLSS, DLSS 3.

Here are the key features of the Ray Tracing Overdrive Mode for Cyberpunk 2077.

• NVIDIA RTX Direct Illumination (RTXDI) gives each neon sign, street lamp, car headlight, LED billboard and TV accurate ray-traced lighting and shadows, bathing objects, walls, passing cars and pedestrians in accurate colored lighting
• Ray-traced indirect lighting and reflections now bounce multiple times, compared to the previous solution’s single bounce. The result is even more accurate, realistic and immersive global illumination, reflections, and self-reflections
• Ray-traced reflections are now rendered at full resolution, further improving their quality
• Improved, more physically-based lighting removes the need for any other occlusion techniques

 

impressive

 

Nvidia - when extreme innovation come with extreme cost

 

I can't wait to replay Cyberpunk with the RT-overdrive update and DLSS 3 The optical flow accelerator sounds like we won't need to switch DLL's over as much.
Racer X demo will be out November incase anyone missed it.

 

DLSS3 looks to be the killer app for ADA. From what I gather, with DLSS3 the tensor cores will be able to add more FPS by themselves (frame generation) without relying of CPU and shader cores, this is utilizing the tensor cores to their maximum potential.

With 35 games at launch supporting DLSS3, seems like integration is simple enough (probably just some minor additions to DLSS2 implementation).

 

It's Frame interpolation though. It will be interesting to see how this is different some something like Valves SteamVR Motion Smooth and the more general Asynchronous SpaceWarp we already have in VR. Or how different it is from the motion smoothing already present on televisions.

 

Frame interpolation from video just add frames between 2 frames (the video processor already process every frame in the video beforehand), you can't interpolate frames in video games because player's movements are unpredictable.
DLSS3 works the same as DLSS2, but instead of drawing pixels on lower-res frames output by shaders to make to high-res ones, tensor cores now can output new frames by themselves.

 

Not having to rely on the render queue and by passing the CPU as a post process is great, gives my CPU a little more breathing room to hold out for RibbonFet archs

Frame interpolation always as a weird animation to it, I'm assuming this will be closer to actual frames than interpolation but we'll see what happens.
Also the optical flow accelerator sounds like it eliminates the ghosting/trailing issues but yeah, we'll see how it is in practice first.

 

Frame interpolation look wrong most of the time, let say the original video has frame 1 and 10 and frame interpolation just add 3 4 5 to it.
The result is we see frame 1 3 4 5 10, look ridiculous that I always turn that crap off in any new TV