Today in Generative Media

iPhones speak your voice; 3D from images without masks; ControlNet with "Segment Anything"

• iPhones will be able to speak in your voice with 15 minutes of training (The Verge)

• AutoRecon: Automated 3D Object Discovery and Reconstruction (CVPR 2023)

• ControlNet on Segment Anything (HuggingFace)

• Character-Aware Models Improve Visual Text Rendering (arXiv)

• Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts (arXiv)

• TextMesh: Generation of Realistic 3D Meshes From Text Prompts (arXiv)