ID-V2V: Identity-preserving video restylization accepted to SIGGRAPH Asia 2026
rsasaki0109 · x · 2026-08-22
ID-V2V is a research exploration accepted to SIGGRAPH Asia 2026 focusing on identity-preserving video restylization.
Core Features:
- Takes a source video plus a stylized keyframe (or multiple) to generate a new video.
- Strictly preserves the source characters' identity and performance, such as subtle expressions, eye gaze, and body movement.
- Adapts the scene, lighting, and style to match the keyframe(s).
Use Case: Enables a "shoot first, restyle later" workflow for visual storytelling. It is intended for demonstration and inspiration only.
More from Multimodal
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Gummy worms as a physics test: Gemini 4 Argon vs. Claude Opus 5.5 elasticity sims — DynamicWebPaige · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Seedance 2.5 demo: stretching one second of an explosion into a 30-second shot — LudovicCreator · 2026-10-16
- Octopus Short Film Made with Grok Imagine, Upscaled via Topaz — creatoroff · 2026-10-16
- Open-sourced 61-second computing history film generated entirely by Muse Spark — sophiamyang · 2026-10-16