Gordon Wetzstein (@GordonWetzstein) / X

Excited to share our new Nature paper! In this work, we propose a new display design that pairs inverse-designed metasurface waveguides with AI-driven holographic displays to enable full-color 3D augmented reality from a compact eyeglasses-like form factor. 1/8

492K

Gordon Wetzstein

@GordonWetzstein

Dec 5, 2023

The future of graphics is here! Generative Rendering is a new approach to generating controllable, long, and temporally consistent videos using pre-trained text-to-image diffusion models and graphics techniques. primecai.github.io/generative_ren…

00:00

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. spmem.github.io 1/3

00:00

Introducing FLARE @CVPR 2025 FLARE is a feed-forward model that simultaneously estimates high-quality camera poses, 3D geometry, and appearance from sparse uncalibrated images. 1/4

00:00

🚀 Just published in Nature Photonics: synthetic aperture waveguide holography—a new path toward ultra-thin, high-quality 3D mixed reality displays. 📄 nature.com/articles/s4156… #Photonics #Holography #MR 1/5

00:00

Most video models 🤯forget the past 🐌slow down over time 🔁rely on bidirectional (not causal) attention Our state-space video world models (SSM) 🧠remember across hundreds of frames ⚡️generate at constant speed ⏩is fully causal, enabling real-time rollout 1/3

00:00

Replying to @GordonWetzstein @manu_gopakumar and 5 others

Project website: computationalimaging.org/publications/h… nature.com/articles/s4158…

Video generation of humans with control over body pose and facial expressions is crucial for a plethora of applications. Towards this goal, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for DiT–based video generation models #SIGGRAPH2025

00:00

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2 rameenabdal.github.io/GaussianShellM…

00:00

Introducing AIpparel @CVPR 2025 - the first multimodal foundation model for digital garments. georgenakayama.github.io/AIpparel/ 1/6

00:00

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. justimyhxu.github.io/projects/grm/ Demo: huggingface.co/spaces/GRM-dem… 1/4

00:00

Excited about receiving the Technical Achievement Award at @IEEEVR "in recognition of pioneering research in the development of computational display and imaging technologies" and be inducted into the VR Academy

Excited to share our new #SIGGRAPH2025 paper! In this work, we show how to combine Gaussian splatting and computer-generated holography using Gaussian Wave Splatting. This enables photorealistic 3D holograms for emerging holographic VR/AR displays. 1/4

00:00

Replying to @GordonWetzstein

We compare video holograms of the same scene produced with a conventional free-space propagation model and with our learned physical waveguide model. The comparison illustrates how our mixture of an analytical waveguide model and AI algorithms enable high-quality holograms. 6/8

00:00

20K