English

OutDreamer: Video Outpainting with a Diffusion Transformer

Computer Vision and Pattern Recognition 2025-06-30 v1

Abstract

Video outpainting is a challenging task that generates new video content by extending beyond the boundaries of an original input video, requiring both temporal and spatial consistency. Many state-of-the-art methods utilize latent diffusion models with U-Net backbones but still struggle to achieve high quality and adaptability in generated content. Diffusion transformers (DiTs) have emerged as a promising alternative because of their superior performance. We introduce OutDreamer, a DiT-based video outpainting framework comprising two main components: an efficient video control branch and a conditional outpainting branch. The efficient video control branch effectively extracts masked video information, while the conditional outpainting branch generates missing content based on these extracted conditions. Additionally, we propose a mask-driven self-attention layer that dynamically integrates the given mask information, further enhancing the model's adaptability to outpainting tasks. Furthermore, we introduce a latent alignment loss to maintain overall consistency both within and between frames. For long video outpainting, we employ a cross-video-clip refiner to iteratively generate missing content, ensuring temporal consistency across video clips. Extensive evaluations demonstrate that our zero-shot OutDreamer outperforms state-of-the-art zero-shot methods on widely recognized benchmarks.

Keywords

Cite

@article{arxiv.2506.22298,
  title  = {OutDreamer: Video Outpainting with a Diffusion Transformer},
  author = {Linhao Zhong and Fan Li and Yi Huang and Jianzhuang Liu and Renjing Pei and Fenglong Song},
  journal= {arXiv preprint arXiv:2506.22298},
  year   = {2025}
}
R2 v1 2026-07-01T03:36:40.853Z