The last two weeks in Generative Media

Hollywood's AI divide; Judge allows AI art lawsuit; Video game actors strike over AI

News

• Hollywood’s Divide on Artificial Intelligence Is Only Growing (Hollywood Reporter)

• Artists’ lawsuit against generative AI makers can go forward, judge says (TechCrunch)

• Video game actors are officially on strike over AI (The Verge)

• Survey: 84% of tech execs back copyright law overhaul for AI era (VentureBeat)

• Spotify is full of AI music, and some say it’s ruining the platform (Fast Company)

• What AI in music can — and can’t — do (Vox)

• AI music startup Lemonaide introduces new collab tool promising ‘ethical’ AI models (Music Business Worldwide)

• Google hires top talent from startup Character.AI, signs licensing deal (Reuters)

• Meta courts celebs like Awkwafina to voice AI assistants ahead of Meta Connect (The Verge)

• Trolls Used Her Face to Make Fake Porn. There Was Nothing She Could Do (New York Times)

• AI Image Generator Made by Stable Diffusion Inventors on Par With Midjourney and DALL-E (PetaPixel)

Software

• gsplat (http://docs.gsplat.studio) now supports multi-GPU distributed training, which nearly linearly reduces the training time and memory footprint. (X)

• CogVideoX-2B Huggingface Space🤗 (HuggingFace)

• Official 🤗 Gradio Demo MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization (HuggingFace)

• Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX (GitHub)

• MoCapade’s public beta is now live. Time for you to show us your moves (X)

Research

• NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields (ECCV 2024, project page)

• Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation (ECCV 2024, project page)

• VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models (ECCV 2024, project page)

• TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling (ECCV 2024, project page)

• ProCreate: Don't Reproduce! Propulsive Energy Diffusion for Creative Generation (ECCV 2024, project page)

• Diffusion Models as Data Mining Tools (ECCV 2024, project page)

• HaLo-NeRF😇 Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections (Eurographics 2024, project page)

• An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion (project page)

• TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models (project page)

• VidGen-1M: A Large-Scale Dataset for Text-to-video Generation (project page)

• Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle (project page)

• PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relighting (arXiv)

Misc

• Here’s a playable video generation model we trained that allows you to control a robot from a first person perspective — generated completely by a video model. (X)

• How to FLUX 💪 (Heather Cooper on Substack)

• powerpoint presentation, the slide title says “Flux AI has new skills”, three bullet points, “good at text”, “prompt comprehension”, “amazing images” (X)

• This one important fact about current AI explains almost everything (Gary Marcus on Substack)

• This one's a collector's item !!! (X)