Today in Generative Media

Taiwan on China's AI disinfo; Dorsey, Musk decry IP laws; Law profs oppose Meta

News and Opinion

• Taiwan says China using generative AI to ramp up disinformation and 'divide' the island (Reuters)

• ‘All-out war’: Jack Dorsey, Elon Musk call for an end to intellectual property laws (Music Business Worldwide)

• Law professors side with authors battling Meta in AI copyright case (TechCrunch)

• Is there a ‘right’ way to use AI in art? (The Verge)

• Deep Learning, Deep Scandal (Gary Marcus on Substack)

• OpenAI, Studio Ghibli: Of Course It's Infringement! "Style" Is Protectable (Peter Csathy on Substack)

• Infinite Realities & The Future of Imaging (Radiance Fields)

• YouTube expands its ‘likeness’ detection technology, which detects AI fakes, to a handful of top creators (TechCrunch)

• DeepMind CEO Demis Hassabis says Google will eventually combine its Gemini and Veo AI models (TechCrunch)

Software and Research

• LAM: Official Pytorch Implementation (GitHub)

• FantasyTalking Realistic Talking Portrait Generation via Coherent Motion Synthesis (project page)

• Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation (project page)

• Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Model (project page)

• 🌸 FlowR: Flowing from Sparse to Dense 3D Reconstructions (project page)

• WonderTurbo:Generating Interactive 3D World in 0.72 Seconds (project page)

• FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution (arXiv)

• MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs (arXiv)

• Disentangled 4D Gaussian Splatting: Towards Faster and More Efficient Dynamic Scene Rendering (arXiv)

• Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video (arXiv)

• Learning Human Perspective in Line Drawings from Single Sketches (arXiv)

• MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection (arXiv)