Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914479134998528 |
|---|---|
| author | Jeon, Inseok Lee, Minhyeok Lee, Seunghoon Kang, Minseok Cho, Suhwan Lee, Sangyoun |
| author_facet | Jeon, Inseok Lee, Minhyeok Lee, Seunghoon Kang, Minseok Cho, Suhwan Lee, Sangyoun |
| contents | Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial context. These limitations lead to intraframe and inter-frame inconsistencies, which become particularly pronounced in dynamic scenes and large outpainting scenarios. To overcome these challenges, we propose Seen-to-Scene, a novel framework that unifies propagationbased and generation-based paradigms for video outpainting. Specifically, Seen-to-Scene leverages flow-based propagation with a flow completion network pre-trained for video inpainting, which is fine-tuned in an end-to-end manner to bridge the domain gap and reconstruct coherent motion fields. To further improve the efficiency and reliability of propagation, we introduce a reference-guided latent propagation that effectively propagates source content across frames. Extensive experiments demonstrate that our method achieves superior temporal coherence and visual realism with efficient inference, surpassing even prior state-of-the-art methods that require input-specific adaptation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14648 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting Jeon, Inseok Lee, Minhyeok Lee, Seunghoon Kang, Minseok Cho, Suhwan Lee, Sangyoun Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial context. These limitations lead to intraframe and inter-frame inconsistencies, which become particularly pronounced in dynamic scenes and large outpainting scenarios. To overcome these challenges, we propose Seen-to-Scene, a novel framework that unifies propagationbased and generation-based paradigms for video outpainting. Specifically, Seen-to-Scene leverages flow-based propagation with a flow completion network pre-trained for video inpainting, which is fine-tuned in an end-to-end manner to bridge the domain gap and reconstruct coherent motion fields. To further improve the efficiency and reliability of propagation, we introduce a reference-guided latent propagation that effectively propagates source content across frames. Extensive experiments demonstrate that our method achieves superior temporal coherence and visual realism with efficient inference, surpassing even prior state-of-the-art methods that require input-specific adaptation. |
| title | Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.14648 |