Today in Generative Media

Adobe's genAI video tools; Tech leaders hold off AI rules; Music biz in tune with GenAI

• Adobe Premiere Pro is getting generative AI video tools — and hopefully OpenAI’s Sora (The Verge)

• Tech Leaders Once Cried for AI Regulation. Now the Message Is ‘Slow Down’ (Wired)

• The music industry must find a way to stay in tune with GenAI (ZDNet)

• Adobe releases Acrobat AI assistant starting at $4.99 a month (CNBC)

• The LLMentalist Effect: how chat-based Large Language Models replicate the mechanisms of a psychic’s con (Out of the Software Crisis)

• SAGA. Innovative Tools for Storytellers.

• AI Likeness Rights Infrastructure: Integrate FameFlow’s AI likeness rights API infrastructure to legally allow your Brands and Agency clients to use celebrities in their AI generated ads. (FameFlow)

• Official 🤗 Gradio Demo - InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models (HuggingFace)

• Probing the 3D Awareness of Visual Foundation Models (CVPR 2024, arXiv)

• The More You See in 2D, the More You Perceive in 3D (project page)

• Taming Latent Diffusion Model for Neural Radiance Field Inpainting (project page)

• GSCore: Efficient Radiance Field Rendering via Architectural Support for 3D Gaussian Splatting (ASPLOS ‘24, PDF)

• CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting (arXiv)

• MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance (arXiv)

• Move Anything with Layered Scene Diffusion (arXiv)

• ChatGPT Can Predict the Future when it Tells Stories Set in the Future About the Past (arXiv) [Peak AI hype has arrived!]

• Spatial brainstorming, powered by AI. With Oxygen, you can have an infinite canvas to capture your inspirations, while connecting them with your environment and elevating them with AI. (X) Code on GitHub.

• Introducing Captions for web. Video editing made simple, thanks to AI — now on a bigger screen. One-click editing, right from your browser. (X)

• Avatar in Motion 1.0🏃‍♂️✨. Move your hands, make gestures, use unique tones of voice, and HeyGen will flawlessly track, translate, and lip-sync your video with any input text. (X)

• Introducing "Character" 🎉🎉 – our latest feature where the character is kept consisent while switching scenes with ease. Experience seamless style transitions while maintaining your character's identity. Explore endless possibilities with Character now! https://app.pixverse.ai (X)

• The CosXL model from StabilityAI might be THE image editing AI we've been waiting for. Just tell it how to change an image with a prompt. (X)

• …the professional matte painter who created this asset, wasn't just "clicking a button" like some people say that is working with AI. (X)

• genAI yearbook page (X)

• Announcing NeurIPS Preschool Track (X)