GIST Scholar
College of Artificial Intelligence
Department of Electrical Engineering and Computer Science
2. Conference Papers
High Fidelity and Real-time Video Face Swapping
- Type
- Conference Paper
- Citation
- 20th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2026
- Issued Date
- 2026-05-25
- Abstract
- We present FaceFlowSwap (FFS), a video faceswapping method that achieves competitive quality with diffusion-based methods while meeting real-time constraints across video domains. FFS comprises a source-identity encoder, a video fusion module that aggregates cross-frame evidence via 3D convolutions and combines it with source-identity features, and a swapper that generates frames with a swapped face. Robustness to pose and motion is achieved through spatiotemporal adversarial learning combined with a source-identityenhancing loss, extended to the spatio-temporal dimension. Our ablations verify the contribution of each component to temporal coherence, controllability, and speed. Evaluated on FaceForensics++ and VFHQ datasets, FFS achieves state-of-theart identity preservation and visual quality while maintaining 21.7 ms processing speed per frame, which matches the real-time condition. © 2026 IEEE.
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Conference Place
- JA
Kyoto
- Appears in Collections:
- Department of Electrical Engineering and Computer Science > 2. Conference Papers
- 파일 목록
-
-
관련 파일이 존재하지 않습니다.
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.