Kakao Brain Brings Big Improvements To The Metaverse With New Face-Swap Tech TechRadar

Representing another milestone in Kakao Brain’s face-swapping research, the company’s paper “Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness” will be presented at the upcoming World Vision Conference. by computer, CVPR 2022[2], for the second consecutive year. This will include an exclusive oral presentation session reserved for the most outstanding papers among the accepted papers (25.33% of the 8,161 submissions were accepted this year). At last year’s event, only 4% of accepted papers had time for an oral presentation in which Kakao Brain was nominated for his outstanding research paper, “HOTR: End-to-End Human- Object Interaction Detection with Transformers”. This year, ‘Smooth-Swap’ not only succeeded in significantly reducing the complexity of its architecture, but also has great market potential, both recognized and awarded by the first conference on computer vision.

A precise and consistent identity gradient[3] is essential for changing a person’s identity without sacrificing high image quality. Trained via supervised contrastive loss, ‘Smooth-Swap’ acquires its stable identity gradient by learning incorporation with greater smoothness. These improvements address the previous model’s weakness of adding handcrafted components and 3D face modeling, which ultimately complicated its design and resulted in sophisticated hyperparameter tuning. Instead, “Smooth-Swap” relies on a simple U-Net-based architecture with a built-in identity integrator to deliver industry-leading performance.

The simple architecture and improved performance of “Smooth-Swap” have not only made the technology competitive in terms of market potential and wider application, but also enable it to cope with face-swap scenarios. more difficult, such as face swapping during video playback. “Smooth-Swap” suggests a differentiated identity integration approach and allows the generator to create higher quality images, especially when changing a subject’s face shape. Thanks to Kakao Brain’s “Smooth-Swap”, which enables fast and stable face swapping, it is expected to develop different types of digital humans such as virtual influencers, show hosts and announcers.

“We are proud and excited to unveil the revolutionary 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 face swapping, bringing us even closer to the incredibly immersive metaverse we’ve always dreamed of, and the digital human services of the future.”

About Kakao Brain

Kakao Brain is a world-leading AI company with unrivaled AI technologies and research and development networks. The company was established by Kakao in 2017 to solve some of the world’s biggest “unthinkable questions” with solutions made possible by its life-changing artificial intelligence technologies. Always at the forefront of innovation in the world of technology, Kakao Brain has developed many revolutionary AI services and models designed to improve the quality of life of thousands of people, including minDALL-E, KoGPT, CLIP/ALIGN and RQ-Transformer. As a global AI pioneer, Kakao Brain has a responsibility to foster a vibrant technology community and a robust R&D ecosystem as part of its mission to create new technology markets with infinite potential. For more information, visit https://KakaoBrain.com/.

[1] Identity integration is a vector representation of a face image used to compare identities. If the representation vectors (or integration vectors) of two faces are sufficiently close, their identities are considered identical.

[2] CVPR (Computer Vision and Pattern Recognition Conference)co-sponsored by the Institute of Electrical and Electronics Engineers (IEEE) and the Computer Vision Foundation (CVF) since 1983, is considered one of the most recognized annual conferences in the computer vision industry, along with the European Conference on Computer Vision (ECCV) and International Conference on Computer Vision (ICCV).

[3] The identity gradient is a training signal telling the face swap model which part needs to be tuned to change the person’s identity accurately.

SOURCE Kakao Brain

We would like to say thanks to the author of this post for this remarkable material

Kakao Brain Brings Big Improvements To The Metaverse With New Face-Swap Tech TechRadar


Discover our social media profiles as well as other related pageshttps://www.ai-magazine.com/related-pages/