This weekend in Generative Media
Adobe, Microsoft AI quality issues; WhatsApp's AI bots; Talk to your TV's Google AI
News
Adobe’s Generative AI Jumps The Shark, Adds Bitcoin to Bird Photo (PetaPixel)
Microsoft is reverting its Bing AI image generator because of quality complaints (The Verge)
WhatsApp really hopes you want to talk with AI bots (The Verge)
Google will use more mics and Gemini AI to get you to talk to your TV (The Verge)
VCs say AI companies need proprietary data to stand out from the pack (TechCrunch)
The Prototype: Study Suggests AI Tools Decrease Critical Thinking Skills (Forbes)
Hands-on jobs to grow fastest, because AI can't touch them (The Register)
Rounded is an AI orchestration platform that lets anyone build an AI voice agent (TechCrunch)
AI could create 78 million more jobs than it eliminates by 2030—report (Ars Technica)
VLC player demos real-time AI subtitling for videos (The Verge)
Smoke, reflections and portals: Adobe’s TransPixar takes AI VFX to the next level (VentureBeat)
Software
Create AI videos & animations in 1-click (CinemaFlow)
Research
👁️ IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images (project page)
Decentralized Diffusion Models (project page)
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution (project page)
Consistent Flow Distillation for Text-to-3D Generation (project page)
SVFR: A Unified Framework for Generalized Video Face Restoration (project page)
Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation (project page)
FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on (project page)
EditAR: Unified Conditional Generation with Autoregressive Models (project page)
The GAN is dead; long live the GAN! A Modern GAN Baseline (arXiv)
GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting (arXiv)
Scaffold-SLAM: Structured 3D Gaussians for Simultaneous Localization and Photorealistic Mapping (arXiv)
Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (arXiv)