cs.CVNov 9, 2026

LongSCOP: Semantically Consistent Long Video Outpainting

Authors: Yu Tang, Zhiyuan You, Zhixiao Wang, Fanghua Yu, Qingyu Zhang, Xiang Yin, Chao Dong, Jinjin Gu

Organizations: Nanjing University · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · The Chinese University of Hong Kong · The University of Hong Kong · 

Abstract

Video out-painting is an important problem, yet existing research focuses primarily on short clips, leaving long video out-painting largely underexplored. Extending video out-painting to long videos poses substantial challenges. A natural solution is iterative out-painting, i.e., generating videos chunk by chunk, but this introduces two major issues: generation instability or even failure caused by inter-chunk inconsistencies and error accumulation, and semantic drift over long temporal horizons. In this paper, we propose LongSCOP, short for Semantically Consistent long Video Out-Painting. First, we introduce a training recipe with three components for smooth and stable long-horizon generation: self-forcing training, latent calibration, and future references. Beyond generation stability, we recognize that the rich temporal context of long videos provides valuable references for maintaining semantic consistency. We therefore develop a VLM-based agent that automatically selects the most informative reference frames from the entire video to maintain consistent subjects, scenes, and backgrounds throughout long-horizon generation. We also construct a high-quality training dataset of 62K video clips. To facilitate research on this underexplored problem, we introduce LVO-Bench, a benchmark curated by human experts to assess long-horizon stability and semantic consistency. Extensive experiments demonstrate that our method outperforms existing approaches in both generation stability and semantic coherence.

Figures & tables

Explore similar work

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

    May 17, 2026Jeongeun Park, Janghyeok Han, Geonung Kim +4Video OutpaintingLong Video Generation

  2. A2^2RD: Agentic Autoregressive Diffusion for Long Video Consistency

    May 7, 2026Do Xuan Long, Yale Song, Min-Yen Kan +2Video Diffusion ModelsLong Video Generation

  3. Recast the Past: Stable Long Video Generation with Full Context Memory

    Oct 20, 2026Yukuo Ma, Cong Liu, Junke Wang +4Long-Horizon Video GenerationMemory-Augmented Video Generation