IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912771253207040 |
|---|---|
| author | Li, Yuanhang Song, Yiren Bai, Junzhe Liang, Xinran Yang, Hu Jin, Libiao Mao, Qi |
| author_facet | Li, Yuanhang Song, Yiren Bai, Junzhe Liang, Xinran Yang, Hu Jin, Libiao Mao, Qi |
| contents | We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal consistency. Video VFX editing is highly challenging because injected effects must blend seamlessly with the background, the background must remain entirely unchanged, and effect patterns must be learned efficiently from limited paired data. However, existing video editing models fail to satisfy these requirements. IC-Effect leverages the source video as clean contextual conditions, exploiting the contextual learning capability of DiT models to achieve precise background preservation and natural effect injection. A two-stage training strategy, consisting of general editing adaptation followed by effect-specific learning via Effect-LoRA, ensures strong instruction following and robust effect modeling. To further improve efficiency, we introduce spatiotemporal sparse tokenization, enabling high fidelity with substantially reduced computation. We also release a paired VFX editing dataset spanning $15$ high-quality visual styles. Extensive experiments show that IC-Effect delivers high-quality, controllable, and temporally consistent VFX editing, opening new possibilities for video creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15635 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning Li, Yuanhang Song, Yiren Bai, Junzhe Liang, Xinran Yang, Hu Jin, Libiao Mao, Qi Computer Vision and Pattern Recognition Artificial Intelligence We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal consistency. Video VFX editing is highly challenging because injected effects must blend seamlessly with the background, the background must remain entirely unchanged, and effect patterns must be learned efficiently from limited paired data. However, existing video editing models fail to satisfy these requirements. IC-Effect leverages the source video as clean contextual conditions, exploiting the contextual learning capability of DiT models to achieve precise background preservation and natural effect injection. A two-stage training strategy, consisting of general editing adaptation followed by effect-specific learning via Effect-LoRA, ensures strong instruction following and robust effect modeling. To further improve efficiency, we introduce spatiotemporal sparse tokenization, enabling high fidelity with substantially reduced computation. We also release a paired VFX editing dataset spanning $15$ high-quality visual styles. Extensive experiments show that IC-Effect delivers high-quality, controllable, and temporally consistent VFX editing, opening new possibilities for video creation. |
| title | IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.15635 |