MUGEN: Interactive Panoramic World Exploration via Camera Control

2026-09-29

AI Summary

This study addresses the coupled challenges of dataset scarcity and the lack of panoramic geometric support in existing models for omnidirectional video generation. To this end, we construct MUGEN, a large-scale 360° video dataset, and propose Wan360, a camera-controllable generative model. Methodologically, we design parameter-free equirectangular projection (ERP)-aware modules and panoramic Plücker embeddings. By integrating periodic longitude Rotary Position Embeddings (RoPE), ERP-aware padding, and randomized yaw-roll augmentation strategies, our approach effectively eliminates longitudinal seam artifacts and polar distortions. Ultimately, this framework achieves high-quality, temporally coherent 360° immersive video generation with precise user-specified camera trajectory control.

Abstract

Interactive panoramic video generation aims to synthesize immersive 360\textdegree{} videos that remain visually coherent while following user-specified camera trajectories during exploration. However, progress is limited by a coupled data-and-model gap: existing panoramic video datasets are often short, weakly annotated, or lack camera trajectories, while existing camera-controlled video generation models are designed for perspective videos and do not directly support panoramic geometry. In this paper, we introduce MUGEN and Wan360 to address these limitations. MUGEN is a large-scale real-world panoramic video dataset tailored to interactive 360-degree world exploration, comprising over 1,300 hours of at least 4K panoramic videos with rich semantic and geometric annotations. Built on MUGEN, we further present Wan360, a camera-controllable interactive panoramic video generation model. Panoramic videos are commonly represented by EquiRectangular Projection (ERP), which unfolds a spherical 360-degree view into a rectangular frame with cyclic longitude seams and pole distortions. To this end, Wan360 introduces three parameter-free ERP-aware components: periodic longitude RoPE for seam-consistent positional encoding, ERP-aware padding for reducing boundary artifacts, and random roll yaw for consistent learning. For camera control, Wan360 uses a panoramic Plücker embedding that represents camera motion with ERP rays rather than perspective pinhole rays. Experiments show that MUGEN serves as a data foundation for panoramic world exploration, and that Wan360 enables high-quality, temporally coherent, camera-controllable 360-degree video generation.

Problem

• interactive panoramic video generation
• camera-controlled video generation
• panoramic dataset
• equiRectangular projection
• 360-degree video

Innovation

• Panoramic Video Generation
• EquiRectangular Projection (ERP)
• Camera Control
• Plücker Embedding
• Periodic RoPE