Today in Generative Media

Music can thrive with AI; Marketers use genAI avatars; Publishers' AI deals in 2024

News

• Music Can Thrive in the AI Era (Wired)

• Marketers balance creepiness and realism as more AI-generated avatars come online (Digiday)

• 2024 in review: A timeline of the major deals between publishers and AI companies (Digiday)

• The internet is filled with fake reviews. Here are some ways to spot them (AP News)

• Google is using Anthropic’s Claude to improve its Gemini AI (TechCrunch)

• How to protect yourself from AI scams this holiday season (NPR)

• AI use cases are going to get even bigger in 2025 (Fast Company)

• Generative AI is now a must-have tool for technology professionals (ZDNet)

• How Hallucinatory A.I. Helps Science Dream Up Big Breakthroughs (New York Times)

• OpenAI lays out its for-profit transition plans (TechCrunch)

Software

• Postshot v0.5 is now availableUnreal Engine Integration, Supports VR Stereo Rendering, Merge Multiple Scenes, Radiance Field Sequence Playback. (X)

• StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos (GitHub)

• MMAudio Comes to Mac! (X)

• Diffusers 0.32.0: New video pipelines, new image pipelines, new quantization backends, new training scripts, and more (GitHub)

• Leffa: Learning Flow Fields in Attention for Controllable Person Image Generation (HuggingFace)

• Arbitrary-steps Image Super-resolution via Diffusion Inversion (GitHub)

• Open WebUI is an extensible, feature-rich, and user-friendly self-hosted [LLM] WebUI designed to operate entirely offline. (GitHub)

Research

• SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction (project page)

• Can Generative Video Models Help Pose Estimation? (project page)

• Personalized Representation from Personalized Generation (project page)

• Automating the Search for Artificial Life with Foundation Models (project page)

• Can Generative Video Models Help Pose Estimation? (project page)

• FaceLift: Single Image to 3D Head with View Generation and GS-LRM (project page)

• IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing (project page)

• CoSurfGS: Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction (project page)

• PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models (project page)

• Parallelized Autoregressive Visual Generation (project page)

• Exploring Dynamic Novel View Synthesis Technologies for Cinematography (arXiv)

• LEDiff: Latent Exposure Diffusion for HDR Generation (arXiv)