-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2022_CVPR, author = {Kim, Jiseob and Lee, Jihoon and Zhang, Byoung-Tak}, title = {Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10779-10788} }
Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness
Abstract
Face-swapping models have been drawing attention for their compelling generation quality, but their complex architectures and loss functions often require careful tuning for successful training. We propose a new face-swapping model called 'Smooth-Swap', which excludes complex handcrafted designs and allows fast and stable training. The main idea of Smooth-Swap is to build smooth identity embedding that can provide stable gradients for identity change. Unlike the one used in previous models trained for a purely discriminative task, the proposed embedding is trained with a supervised contrastive loss promoting a smoother space. With improved smoothness, Smooth-Swap suffices to be composed of a generic U-Net-based generator and three basic loss functions, a far simpler design compared with the previous models. Extensive experiments on face-swapping benchmarks (FFHQ, FaceForensics++) and face images in the wild show that our model is also quantitatively and qualitatively comparable or even superior to the existing methods.
Related Material