Today in Generative Media
AI invades the arts; 94% of AI college writing undetected; World Labs' AI 3D scenes
News
Study: 94% Of AI-Generated College Writing Is Undetected By Teachers (Forbes)
World Labs’ AI can generate interactive 3D scenes from a single photo (TechCrunch)
One million public Bluesky posts scraped for AI training (Mashable)
Certain names make ChatGPT grind to a halt, and we know why (Ars Technica)
The company behind Arc is building a new AI web browser called Dia (The Verge)
Software
Julius is a great AI tool for analyzing and visualizing datasets (Fast Company)
MoSca: A Modern 4D Reconstruction System for Monocular Videos (GitHub)
HunyuanVideo: A Systematic Framework For Large Video Generation Model Training (GitHub)
Research
TEXGen: a Generative Diffusion Model for Mesh Textures (SIGGRAPH Asia 2024 project page)
Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors (project page)
🛹 RollingDepth: Video Depth without Video Models (project page)
One-Step Diffusion Model for Face Restoration (project page)
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (project page)
ScribbleLight: Single Image Indoor Relighting with Scribbles (project page)
ID-Patch: Robust ID Association for Group Photo Personalization (project page)
Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (project page)
MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (project page)
Pathways on the Image Manifold: Image Editing via Video Generation (arXiv)