cs.CVNov 17, 2026

Evolve in Panorama, Render in View: Panoramic World State Evolution for Video World Models

Authors: Longtao Jiang, Mingfei Han, Jianmin Bao, Tingjun Dai, Jinjie Wei, Zhiran Zhang, Xin Tao, Zhihui Li, 

Organizations: Mohamed bin Zayed University of Artificial Intelligence · Kuaishou Technology

Abstract

Video world models should maintain a world that keeps evolving as the viewpoint changes. Yet when the camera turns away and returns, current models often freeze the unobserved scene, lose objects, or change their appearance, because content outside the view has no representation that keeps changing. We present PanoEvo, which uses a Panoramic Evolver to evolve the world state in the latent space of a panoramic video diffusion model, where every viewing direction is present at every time step, so the scene evolves whether or not it is observed. Existing panoramic video models are not trained to evolve a scene from a single image or the objects within it, so we build PanoEvo-Data, an event-centric dataset from real 360° videos, and train the Panoramic Evolver coarse-to-fine as an image-to-panoramic-video model. Since each view covers only a small part of the low-resolution panorama, directly projected views are blurry and often show low-quality details or structural errors. A Perspective Renderer, built on a perspective video diffusion model, reads this state via latent-space projection and direction-restricted cross-attention to render sharp, high-quality views. PanoEvo achieves the best overall score among 23 publicly evaluated models on WRBench and the highest total score on STEVO-Bench. Code, models, and data will be released.

Figures & tables

Explore similar work

CardsList
  1. AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video

    Sep 13, 2026Jiaming Tan, Mingliang Zhai, Zhen Li +3Video World ModelsVideo Generation

  2. PanoWorld: Real-World Panoramic Generation

    Jul 10, 2026Haoyuan Li, Dizhe Zhang, Yuemei Zhou +7World Model LearningWorld Models