Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
This work addresses the problem of realistic face swapping in cinematic videos for film and entertainment production, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of achieving high fidelity and temporal consistency in video face swapping for film production by introducing LivingSwap, a video reference guided model that uses keyframe conditioning and temporal stitching. The method achieves state-of-the-art results, seamlessly integrating target identity with source video attributes and reducing manual effort.
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