Semantic Scholar Open Access 2021 55 sitasi

Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness

Jiseob Kim Ji-Hyun Lee Byoung-Tak Zhang

Abstrak

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, $Face-Forensics++$) and face images in the wild show that our model is also quantitatively and qualitatively comparable or even superior to the existing methods.

Topik & Kata Kunci

Penulis (3)

J

Jiseob Kim

J

Ji-Hyun Lee

B

Byoung-Tak Zhang

Format Sitasi

Kim, J., Lee, J., Zhang, B. (2021). Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness. https://doi.org/10.1109/CVPR52688.2022.01051

Akses Cepat

Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
55×
Sumber Database
Semantic Scholar
DOI
10.1109/CVPR52688.2022.01051
Akses
Open Access ✓