This fall, gamers will be able to enjoy more realistic play thanks to the latest Nvidia AI neural rendering techniques in DLSS 3.5 with Ray Reconstruction. Unlike the boost Nvidia provided with DLSS 3’s Frame Generation add-on, DLSS 3.5 boosts ray tracing across the RTX GPU lineup. Nvidia’s new DLSS 3.5 release isn’t only for gamers. Ray Reconstruction is also coming to third-party 3D creator tools like Chaos Vantage and D5 Render as well as the Nvidia Omniverse line of products, providing more accurate previews, among other advantages. Continue reading Gaming Gets Boost with Nvidia DLSS 3.5 AI Neural Rendering

In the run-up to SIGGRAPH 2022, August 8-11 at the Vancouver Convention Center, Nvidia is unveiling some splashy designs, including what is described as the world’s thinnest VR glasses (just 2.5mm). Developed in conjunction with Stanford University, the team says the new VR headset can easily be modified to achieve a 120-degree diagonal field-of-view (though the initial prototypes are much narrower in scope). The lightweight glasses provide a true holographic display but can also display flat images. Most current VR headsets achieve depth by converging flat images for a stereoscopic view. Continue reading Nvidia and Stanford Co-Develop World’s Thinnest VR Headset

A new technique for machine learning that allows computers to use algorithms that turn 2D images into 3D is stirring a lot of excitement in the worlds of games, computer graphics and AI. The approach relies on “neural rendering,” which uses a neural network to generate 3D imagery from multiple 2D snapshots. A merger of concepts from the worlds of computer graphics and artificial intelligence, neural rendering gained steam in 2020 when researchers at Google and UC Berkeley demonstrated how a neural network could photorealistically capture a scene in 3D after ingesting several 2D snapshots. Continue reading Algorithms Use NeRFs to Instantly Convert 2D Images to 3D