Today in Generative Media

AI Jimmy Stewart reads bedtime stories; AI talks to the dead; AI makes digital clones

• Can’t Sleep? Listen to an A.I.-Generated Bedtime Story From Jimmy Stewart. (New York Times)

• Using A.I. to Talk to the Dead (New York Times)

• The people creating digital clones of themselves (BBC)

• Opinion: Should A.I. Accelerate? Decelerate? The Answer Is Both. (New York Times)

• Audiobox is Meta’s new foundation research model for audio generation (Meta)

• MotionDirector: Motion Customization of Text-to-Video Diffusion Models (HuggingFace)

• Photorealistic Video Generation with Diffusion Models (project page)

• Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D (project page)

• Learn to Optimize Denoising Scores for 3D Generation - A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting (project page)

• MonoNPHM: Dynamic Head Reconstruction from Monocular Videos (project page)

• HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video (ICCV 2023 project page)

• Gaussian Splatting SLAM (project page)

• Get your ideas into functioning AR filters in real-time (X)