DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jinxiu, Lin, Shaoheng, Li, Yinxiao, Yang, Ming-Hsuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909824545980416
author Liu, Jinxiu
Lin, Shaoheng
Li, Yinxiao
Yang, Ming-Hsuan
author_facet Liu, Jinxiu
Lin, Shaoheng
Li, Yinxiao
Yang, Ming-Hsuan
contents The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360$°$ 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 $\href{https://dynamic-scaler.pages.dev/new}{https://dynamic-scaler.pages.dev/new}$.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11100
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes
Liu, Jinxiu
Lin, Shaoheng
Li, Yinxiao
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360$°$ 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 $\href{https://dynamic-scaler.pages.dev/new}{https://dynamic-scaler.pages.dev/new}$.
title DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11100