HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

TL;DR

HL-OutPaint is a novel high-resolution video outpainting framework that employs a coarse-to-fine approach with a global guidance mechanism to ensure spatial and temporal consistency in long, wide-range videos.

Contribution

It introduces a global-local frame swapping mechanism for constructing global coarse guidance, enabling stable, coherent outpainting of long videos with large spatial extrapolation.

Findings

Outperforms existing methods in wide spatial extrapolation tasks.

Achieves stable and coherent generation for long video sequences.

Effectively encodes long-term structure and short-term dynamics.

Abstract

Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support such use cases, it must enable large spatial extrapolation over long sequences. However, most existing methods address only one of these challenges or lack explicit mechanisms for ensuring global spatio-temporal consistency, leading to notable limitations. In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. Our approach follows a coarse-to-fine strategy with a two-stage pipeline. We first construct Global Coarse Guidance (GCG), a low-resolution representation that captures global structure and dominant motion across the video. Unlike naive downsampling, GCG is built via a novel global-local frame swapping mechanism that couples sparse global keyframes with local temporal windows and exchanges information during sampling. This enables GCG to encode both long-term structural consistency and short-term temporal dynamics in a unified representation. Guided by this representation, HL-OutPaint then performs high-resolution outpainting to generate spatially detailed and temporally consistent content. By separating global structure modeling from fine-grained synthesis, our framework achieves stable, coherent generation for large spatial expansion and long video sequences. Extensive experiments show that HL-OutPaint outperforms existing methods in challenging scenarios involving wide spatial extrapolation and long video sequences.