Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
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_ | 1866910098540986368 |
|---|---|
| author | Luo, Zekai Du, Zongze Zhu, Zhouhang Zhong, Hao Zhu, Muzhi Wang, Wen Xi, Yuling Jing, Chenchen Chen, Hao Shen, Chunhua |
| author_facet | Luo, Zekai Du, Zongze Zhu, Zhouhang Zhong, Hao Zhu, Muzhi Wang, Wen Xi, Yuling Jing, Chenchen Chen, Hao Shen, Chunhua |
| contents | Video face swapping is crucial in film and entertainment production, where achieving high fidelity and temporal consistency over long and complex video sequences remains a significant challenge. Inspired by recent advances in reference-guided image editing, we explore whether rich visual attributes from source videos can be similarly leveraged to enhance both fidelity and temporal coherence in video face swapping. Building on this insight, this work presents LivingSwap, the first video reference guided face swapping model. Our approach employs keyframes as conditioning signals to inject the target identity, enabling flexible and controllable editing. By combining keyframe conditioning with video reference guidance, the model performs temporal stitching to ensure stable identity preservation and high-fidelity reconstruction across long video sequences. To address the scarcity of data for reference-guided training, we construct a paired face-swapping dataset, Face2Face, and further reverse the data pairs to ensure reliable ground-truth supervision. Extensive experiments demonstrate that our method achieves state-of-the-art results, seamlessly integrating the target identity with the source video's expressions, lighting, and motion, while significantly reducing manual effort in production workflows. Project webpage: https://aim-uofa.github.io/LivingSwap |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality Luo, Zekai Du, Zongze Zhu, Zhouhang Zhong, Hao Zhu, Muzhi Wang, Wen Xi, Yuling Jing, Chenchen Chen, Hao Shen, Chunhua Computer Vision and Pattern Recognition Video face swapping is crucial in film and entertainment production, where achieving high fidelity and temporal consistency over long and complex video sequences remains a significant challenge. Inspired by recent advances in reference-guided image editing, we explore whether rich visual attributes from source videos can be similarly leveraged to enhance both fidelity and temporal coherence in video face swapping. Building on this insight, this work presents LivingSwap, the first video reference guided face swapping model. Our approach employs keyframes as conditioning signals to inject the target identity, enabling flexible and controllable editing. By combining keyframe conditioning with video reference guidance, the model performs temporal stitching to ensure stable identity preservation and high-fidelity reconstruction across long video sequences. To address the scarcity of data for reference-guided training, we construct a paired face-swapping dataset, Face2Face, and further reverse the data pairs to ensure reliable ground-truth supervision. Extensive experiments demonstrate that our method achieves state-of-the-art results, seamlessly integrating the target identity with the source video's expressions, lighting, and motion, while significantly reducing manual effort in production workflows. Project webpage: https://aim-uofa.github.io/LivingSwap |
| title | Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07951 |