NVIDIA's Lyra 2.0 turns a single image into an explorable, consistent 3D world
NVIDIAAI · x · 2026-11-07
NVIDIA will showcase Lyra 2.0 at SIGGRAPH Asia 2026 (Dec 1–4, Kuala Lumpur): it combines video generation with 3D reconstruction to build explorable environments from a single image along a user-chosen camera path. Lyra draws on earlier views and learns to correct accumulating visual errors, keeping the world consistent as you explore and revisit places. Paper, code, and demos are available. NVIDIA's sessions also cover ROS 2 simulation in Isaac Sim, 3D Gaussian Splatting, Cosmos 3 physical AI, and robot learning with Isaac Lab and Newton.
Related event: NVIDIA Unveils Lyra 2.0: Explorable 3D Worlds from a Single Image(4 posts)→
More from Multimodal
- Premiere Pro Beta Adds Generative Remove for Tracking and Erasing Objects on Timeline — Mr_AllenT · 2026-11-07
- Phone-captured scenes reconstructed at stunning quality with Echo-3 — risingodegua · 2026-11-07
- AI rotoscoping workflow today: LTX 2.5 Alpha LoRA + SAM3 + BiRefNet, layered ProRes — PurzBeats · 2026-11-07
- Custom H3 I2V/REF2V ComfyUI workflow: 20s video in 22 minutes on a 3090, controlling 5 characters — EQLMonk · 2026-11-07
- Flux Max test: mantis shrimp vs white shark prompt fails hilariously, rest looks cinematic — flowersslop · 2026-11-07
- AI video of a cat approving a transaction, made with Seedance 2.5 — prompt included — azed_ai · 2026-11-07