Today in Generative Media
Extract anything from videos; Free code AI from HuggingFace; SIGGRAPH '23 research papers
Just with a text, this AI tool extracts anything from videos such as action, objects, text on screen, speech, and people (Twitter, twelvelabs.io)
Hugging Face and ServiceNow release a free code-generating model (TechCrunch)
Live 3D Portrait: Real-Time Radiance Fields for Single-Image Portrait View Synthesis (SIGGRAPH 2023)
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters (SIGGRAPH 2023) + explained on Twitter.
Learning Physically Simulated Tennis Skills from Broadcast Videos (SIGGRAPH 2023)