ResearchModelsTools

Microsoft Research unveils Mirage to give video generation persistent spatial memory

Microsoft Research and collaborators present Mirage, a video world model that stores spatial memory as the model's internal image features rather than pixel point clouds.

In detail

  • Stores internal image features in 3D space slots instead of colored point clouds
  • Projects stored features directly onto target camera views, skipping rendering and re‑encoding
  • Generates videos in segments, writing stable geometry back into growing memory while filtering out moving objects and sky
  • Built on Alibaba’s Wan2.2 with a small add‑on module teaching the model to use the new memory

Why it matters

Avoiding costly pixel rendering reduces compute and memory use while keeping scene structure consistent during long camera moves — useful for companies building simulations, virtual tours, or long‑take video generation.

For you Evaluate whether your video or simulation pipelines could benefit from feature‑based spatial memory; plan pilots for models that maintain long‑term scene coherence.

← All news

Summaries are generated automatically and link to the original source.