DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes

TL;DR

DynamicScaler is a novel diffusion-based method that enables seamless, scalable, and high-quality panoramic video generation for immersive AR/VR applications, maintaining coherence across arbitrary scene sizes.

Contribution

It introduces a spatially scalable diffusion model with an Offset Shifting Denoiser and Global Motion Guidance for coherent panoramic dynamic scene synthesis.

Findings

Achieves superior content and motion quality in panoramic videos.

Maintains constant VRAM usage regardless of output resolution.

Provides a training-free, efficient solution for dynamic scene creation.

Abstract

The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360${\deg}$ panoramic video. However, most video diffusion models are constrained by limited resolution and aspect ratio, which restricts their applicability to scene-level dynamic content synthesis. In this work, we propose $\textbf{DynamicScaler}$, addressing these challenges by enabling spatially scalable and panoramic dynamic scene synthesis that preserves coherence across panoramic scenes of arbitrary size. Specifically, we introduce a Offset Shifting Denoiser, facilitating efficient, synchronous, and coherent denoising panoramic dynamic scenes via a diffusion model with fixed resolution through a seamless rotating Window, which ensures seamless boundary transitions and consistency across the entire panoramic space, accommodating varying resolutions and aspect ratios. Additionally, we employ a Global Motion Guidance mechanism to ensure both local detail fidelity and global motion continuity. Extensive experiments demonstrate our method achieves superior content and motion quality in panoramic scene-level video generation, offering a training-free, efficient, and scalable solution for immersive dynamic scene creation with constant VRAM consumption regardless of the output video resolution. Project page is available at $\href{https://dynamic-scaler.pages.dev/new}{https://dynamic-scaler.pages.dev/new}$.