South-Korea based AI startup Kakao Brain makes advancements to its face-swapping technology. The company that recently raised $4.4 million investment from RECON Labs announced the newest version of the technology, Smooth-Swap, which is designed to expand the capabilities of smooth face swapping through enhanced identity embedding.
The new version of the technology has replaced complex external modules of existing systems with an integrated smooth identity embedder, which in turn facilitates faster, more stable face swapping.
Smooth-Swap is trained via supervised contrastive loss that helps acquire its stable identity gradient by learning embedding with a higher smoothness. This new improvement address the earlier model’s weakness of adding handcrafted components and 3D face modelling which ultimately complicated its design and entailed sophisticated hyperparameter tuning. Instead, ‘Smooth-Swap’ relies on a simple U-Net-based architecture with an integrated smooth identity embedder to deliver cutting-edge performance.
The enhanced, simple architecture and performance of Smooth-Swap allow it to face more challenging face-swapping scenarios such as face swapping during video playback. ‘Smooth-Swap’ suggests a differentiated identity embedding approach and empowers the generator to create higher-quality images, especially when changing a subject’s face shape. Through Kakao Brain’s ‘Smooth-Swap,’ which enables fast and stable face swapping, it is expected to develop various kinds of digital humans such as virtual influencers, show hosts, and announcers.
“We are proud and excited to unveil the ground-breaking face-swapping technology, ‘Smooth-Swap,’ to the world,” said Kim Il-doo, CEO of Kakao Brain. “I strongly believe this technology will accelerate innovation in the face-swapping sphere, bringing us another step closer to the incredibly immersive metaverse we always dreamed of as wells as the digital human services of the future.”
