Wonder: Real-Time Interactive 3D World Model from Adobe and Johns Hopkins University
yuyinzhou_cs · x · 2026-07-30
Wonder is a real-time, camera-controllable world model that turns an image or video into an explorable 3D world. Users can move the camera, uncover unseen regions, revisit the past, and generate minute-long coherent videos at 16 FPS. It features 6-DoF camera control, constant latency, and long-term consistency through system-level co-design of control representation, memory mechanism, and training strategy. Project page and paper are available; code and HuggingFace model coming soon.
Related event: Adobe and JHU Unveil Real-Time 3D World Model 'Wonder'(3 posts)→
More from Multimodal
- Tim Burtonise V1 Released: A Custom Style Model for Krea2 — Fluid_Kaleidoscope17 · 2026-07-30
- Seedance 2 Video Model Test: Life in a Western Town — Necessary-Use-3820 · 2026-07-30
- Creator Debuts First Episode of AI-Generated 'Odyssey' Short Film — DavidmComfort · 2026-07-30
- Fan-Made Music Video for Skrillex's 'Kyoto' Created Entirely with AI — Procyon87 · 2026-07-30
- nano banana pro in Action: Generating Cinematic 3x3 Storyboards — techhalla · 2026-07-30
- Creator Recreates a True Story Using AI Video Generation — Daniel_Ai_VFX · 2026-07-30