OutDreamer: Video Outpainting with a Diffusion Transformer

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhong, Linhao, Li, Fan, Huang, Yi, Liu, Jianzhuang, Pei, Renjing, Song, Fenglong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913915475066880
author Zhong, Linhao
Li, Fan
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Song, Fenglong
author_facet Zhong, Linhao
Li, Fan
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Song, Fenglong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OutDreamer: Video Outpainting with a Diffusion Transformer
Zhong, Linhao
Li, Fan
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Song, Fenglong
Computer Vision and Pattern Recognition
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.
title OutDreamer: Video Outpainting with a Diffusion Transformer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.22298