Demo

TED Talk

**Face-ing Our Realistic Digital Self** [**`TED`**](https://www.ted.com/talks/koki_nagano_face_ing_our_realistic_digital_self) / [**`TEDxCharlottesville`**](https://www.youtube.com/watch?v=HeC6Id8t2pg)

What You See Is What You GAN

**Rendering Every Pixel for High-Fidelity Geometry in 3D GANs** [**`Project`**](https://research.nvidia.com/labs/nxp/wysiwyg/)

3D Diffusion

**GeNVS: Generative Novel View Synthesis with 3D-Aware Diffusion Models** [**`Project`**](https://nvlabs.github.io/genvs/), [**`Code`**](https://www.youtube.com/watch?v=MVUQ5iJCmKs)

AI-Mediated 3D Video Conferencing

**AI-Mediated 3D Video Conferencing** [**`SIGGRAPH Demo`**](https://research.nvidia.com/labs/nxp/3dvc-siggraph-etech/), [**`Computex Keynote`**](https://www.youtube.com/watch?v=MVUQ5iJCmKs)

Live 3D Portrait

**Real-Time Radiance Fields for Single-Image Portrait View Synthesis** [**`Project`**](https://research.nvidia.com/labs/nxp/lp3d/)

Authenticating Avatars

**Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos** [**`Project`**](https://research.nvidia.com/labs/nxp/avatar-fingerprinting/)

Detecting Diffusion Model-Generated Images

**On the detection of synthetic images generated by diffusion models** [**`Paper`**](https://arxiv.org/abs/2211.00680), [**`Code`**](https://github.com/grip-unina/DMimageDetection)

Neural Portrait Relighting

**Lumos: Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation** [**`Project`**](https://deepimagination.cc/Lumos/), [**`Demo`**](http://imaginaire.cc/Lumos/)

New 3D GAN

**Efficient Geometry-aware 3D Generative Adversarial Networks** [**`Project`**](https://nvlabs.github.io/eg3d/), [**`Code`**](https://github.com/NVlabs/eg3d)

StyleGAN3 Detectors

**Detecting images generated by the latest never-before-seen GAN** [**`Project`**](https://github.com/NVlabs/stylegan3-detector), [**`Blog`**](https://blogs.nvidia.com/blog/2021/11/11/how-researchers-use-nvidia-ai-to-help-mitigate-misinformation/)