PaperScope
LIVE · 2026-09-15 05:40 UTC

AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video

Jiaming Tan, Mingliang Zhai, Zhen Li, Yuwei Wu, Chuanhao Li, Kaipeng Zhang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.14462 v1
Category
Submitted
2026-09-13

Abstract

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatial coverage is typically obtained by synthesizing full-sphere videos or constructing explicit 3D representations. Motivated by the complementary roles of global context and selective local acuity in visual perception, we present AlayaVista, a camera-controllable streaming video world model that decouples panoramic world evolution from perspective observation synthesis. Given a single perspective image, AlayaVista constructs a 360-degree scene prior using a pretrained panorama expansion model and then evolves the scene as a camera-conditioned panoramic latent state. A latent viewport renderer maps this state to the requested perspective video latents, while a perspective refiner restores details, suppresses artifacts, and performs super-resolution. To support efficient streaming, we adapt the panoramic generator to chunk-autoregressive generation and distill both panoramic generation and perspective refinement into few-step processes. To provide the supervision required by this design, we construct MUGEN, a large-scale real-world panoramic video dataset containing 1,318 hours of videos at resolutions of at least 4K, together with rich semantic and geometric annotations.

Comment: Project page: https://alaya-lab.github.io/AlayaVista

arXiv abs page · PDF · same-day batch