This weekend in Generative Media

AI hallucinations, plagiarism, copyright infringement, voice-cloning, and stereotypes

• In Defense of AI Hallucinations (Wired)

• Generative AI Has a Visual Plagiarism Problem (IEEE Spectrum)

• Microsoft and OpenAI sued for copyright infringement by nonfiction book authors in class action claim (NBC News)

• Mickey Mouse and Darth Vader smoking pot: AI image generators play fast and loose with copyrighted characters (Tom’s Hardware)

• Uncle Sam will pay for your big ideas to end AI voice-cloning fraud (The Register)

• AI imaging software generates a gallery of stereotypes, say Univ. of Washington researchers (GeekWire)

• Wizards Of The Coast, ‘Apex Legends’ Under Fire For AI Art (Forbes)

• Text2Immersion: Generative Immersive Scene with 3D Gaussians (project page)

• NViST: In the Wild New View Synthesis from a Single Image with Transformers (project page)

• En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (project page)

• Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis (arXiv)

• A local video animator using Replicate and stable-video-diffusion. (GitHub)

• 2024 will be the year of AI influencers... Fully generated characters that can engage, entertain, and earn! (X)

• The account @BellaMorne, which claims to be from Washington, DC, is using images of model Celine Farach, and an AI-generated profile picture, as a disguise, while they make revenue by making tweets about Palestine and promoting Donald Trump. (X)

• Video to Papercraft Exploration 🛹🤘🏻 (X)

• Can you spot Waldo? (X)