Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness
This work addresses the problem of complex and unstable training for face-swapping models, offering a simpler alternative for researchers and practitioners, though it is incremental as it builds on existing U-Net architectures.
The authors tackled the complexity and instability in training face-swapping models by proposing Smooth-Swap, which uses a smooth identity embedding trained with supervised contrastive loss, resulting in a simpler U-Net-based design that achieves comparable or superior performance on benchmarks like FFHQ and FaceForensics++.
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.