This weekend in Generative Media

GenAI tramples authors; China's Sora competitor Vidu; AI startups face reality

• Opinion: Generative AI is generating astronomical profits by trampling authors and publishers (The Hill)

• China's first Sora-level text-to-video large model Vidu unveiled (China Daily)

• A.I. Start-Ups Face a Rough Financial Reality Check (New York Times)

• A Baltimore-area teacher is accused of using AI to make his boss appear racist (NPR)

• 3 things we learned from professional creatives about their hopes for AI (Google Keyword blog)

• Say hello to the future of Rotoscoping with Hotspring’s latest innovation, Slapshot – a cutting-edge machine learning workflow that generates fast Roto WIPs of anything, at any resolution. (Hotspring)

• Interactive3D🪄: Create What You Want by Interactive 3D Generation (CVPR 2024, project page)

• TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024, project page)

• Make-it-Real: Unleashing Large Multimodal Model's Ability for Painting 3D Objects with Realistic Materials (project page)

• NeRF-XL: Scaling NeRFs with Multiple GPUs (project page)

• ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving (project page)

• GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal (project page)

• CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models (project page)

• ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning (project page)

• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (arXiv)

• OMEGAS: Our method extracts meshes from 3D Gaussian Splatting reconstructions and build hybrid representations that enable easy composition and animation in Gaussian Splatting scenes by manipulating the mesh. (GitHub)

• OpenVoice: Instant voice cloning. Runs local on any computer. (X)

• Why does the new Artificial Intelligence Safety and Security Board have so many members with clear vested interests in rapid, unregulated AI adoption, and so few who have AI expertise without those vested interests? (X)

• Can AI create better VFX? Lots of VFX don’t look great because they don’t know what they’re lighting to on set. Using a variety of AI tools, we can now move fluidly between pre and post. (X)

• video gen'ed directed by my voice in 2min (X)