Today in Generative Media

Pushing AI copyright limits; Controversial AI ads; African labor shapes AI English

• How One Author Pushed the Limits of AI Copyright (Wired)

• A24’s New AI-Generated ‘Civil War’ Ads Generate Controversy (Hollywood Reporter)

• TechScape: How cheap, outsourced labour in Africa is shaping AI English (The Guardian)

• OpenAI winds down AI image generator that blew minds and forged friendships in 2022 (Ars Technica)

• Documentary Producers Set Best Practices for Generative-AI Use in Film (IndieWire)

• AI Computing Is on Pace to Consume More Energy Than India, Arm Says (Yahoo/Bloomberg)

• Dr. Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments (CVPR 2024, project page)

• Transforming a Non-Differentiable Rasterizer into a Differentiable One with Stochastic Gradient Estimation (I3D, project page)

• VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (project page)

• Factorized Diffusion: Perceptual Illusions by Noise Decomposition (project page)

• InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior (project page)

• RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting (project page)

• Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing (project page)

• Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks (arXiv)

• Long-form music generation with latent diffusion (arXiv)

• The Chinchilla scaling paper by Hoffmann et al. has been highly influential in the language modeling community. We tried to replicate a key part of their work and discovered discrepancies. (X)

• Had the opportunity to collaborate with Corridor Crew to develop VFX with AI to present at an annual event hosted by the HPA (Hollywood Press Association) as a demo (X)

• Create your own at http://discord.gg/viggle. Use our template to make the hardest Lil Yachty vibe video in just 5 mins! (X)