Map2Video uses maps and street view imagery to direct AI video of real locations
ryosuzk · x · 2026-11-04
Map2Video is a research project for controlling AI-generated videos set in real-world locations: it plans and directs generated shots using maps and 360° street view imagery.
- Being presented at UIST 2026: talk Tuesday 4:33 PM (Columbus), demo 6–9 PM at Ontario Exhibit Hall
- Relevant to controllable video generation and previsualization workflows
More from Multimodal
- Creator Teases Timed-Lyric AI Video Following Instrumental Release — Kyrannio · 2026-11-04
- One evening, one 256MP image: isometric map of 12.66 km² of downtown Toronto drawn with a Qwen-Image LoRA — CSProfKGD · 2026-11-04
- Electricity per AI image measured across RTX GPUs: ~3-10 cents per 1,000 images with FLUX.2 klein — strata2signal · 2026-11-04
- Topaz Labs launches Wonder 4, a one-click MoE-based upscale/sharpen/denoise model — aziz4ai · 2026-11-04
- Higgsfield x vibe: single-prompt TV-ready AI commercials via MCP — Aiden_Tech_Ai · 2026-11-04
- Dev trains and releases a Pose Control LoRA for Krea-2 image generation — elephant-knight · 2026-11-04