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.
More from Multimodal
- Fish Audio's open-weight Drama 3 voice model claims top emotive quality across 83 languages — mhdfaran · 2026-10-16
- Claude Opus 5.5 makes a pure-code Halloween animation starring bots trick-or-treating for tokens — sattvi · 2026-10-16
- 1,290-line commit lands MOSS Image support in ostris/ai-toolkit — ostrisai · 2026-10-16
- Ostris AI Toolkit adds training support for OpenMOSS's MOSS-Image-SFT model — ostrisai · 2026-10-16
- Nokia vs iPhone, car edition: AI image shows Tesla Roadster hovering over a Porsche — vaibhavbetter · 2026-10-16
- Midjourney multi-sref weight mixing recipe for cinematic light & motion portraits — michaelrabone · 2026-10-16