This weekend in Generative Media

Publishers, journalists worry; TV craft artists use AI; ElevenLabs' genAI sound effects

• Google’s A.I. Search Leaves Publishers Scrambling (New York Times)

• Journalists “deeply troubled” by OpenAI’s content deals with Vox, The Atlantic (Ars Technica)

• TV Craft Artists on Using AI in Your Favorite Shows: ‘It’s Made Us Much, Much More Creative’ (IndieWire)

• ElevenLabs moves beyond speech with AI-generated Sound Effects (VentureBeat)

• ElevenLabs debuts AI-powered tool to generate sound effects (TechCrunch)

• Aftershoot: Hours Worth of Editing Reduced to Minutes (Fstoppers)

• Exactly.ai secures $4M to help artists use AI to scale up their output (TechCrunch)

• What AI thinks a beautiful woman looks like (Washington Post)

• Creators are turning away from some AI tools, new data shows (Business Insider)

• 3D Neural Edge Reconstruction (CVPR 2024, project page)

• NeRF On-the-go Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024, project page)

• GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction (project page)

• SuperGaussian: Repurposing Video Models for 3D Super Resolution (project page)

• GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping (project page)

• Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention (project page)

• Intrinsic Image Decomposition via Ordinal Shading (project page)

• PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher (arXiv)

• ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching (arXiv)

• VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence (arXiv)

• HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (arXiv)

• DualGS: Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos (YouTube)

• 🎞️ ToonCrafter is now on 🥪 tost.ai 🥳 with RunPod's serverless RTX A6000 and A40 (X)

• Here's the first release of my consistent-character model on Replicate. It uses InstantID, IPAdapter, Controlnet and FaceDetailer, with SDXL Lightning. (X)

• "Is there actually a new art form here? That's not a game and not a movie. It's something in the middle." (X)

• There is no generative AI in Beyond the Spider-Verse and there never will be. One of the main goals of the films is to create new visual styles that have never been seen in a studio CG film, not steal the generic plagiarized average of other artists’ work. (X) lmao they already used "AI" in their pipeline (which absolutely would've counted as "generative" if people want to quibble) -- one of their people was literally at CVPR. (X)