BlendFace: Re-designing Identity Encoders for Face-Swapping

Kaede Shiohara, Takafumi Taketomi, Xingchao Yang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• mapooon/blendface — marked official in Papers with Code; named in the paper
• code-implementation1/Code9

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The great advancements of generative adversarial networks and face recognition models in computer vision have made it possible to swap identities on images from single sources. Although a lot of studies seems to have proposed almost satisfactory solutions, we notice previous methods still suffer from an identity-attribute entanglement that causes undesired attributes swapping because widely used identity encoders, e.g., ArcFace, have some crucial attribute biases owing to their pretraining on face recognition tasks. To address this issue, we design Blend-Face, a novel identity encoder for face-swapping. The key idea behind BlendFace is training face recognition models on blended images whose attributes are replaced with those of another mitigates inter-personal biases such as hairsyles. BlendFace feeds disentangled identity features into generators and guides generators properly as an identity loss function. Extensive experiments demonstrate that BlendFace improves the identity-attribute disentanglement in face-swapping models, maintaining a comparable quantitative performance to previous methods. The code and models are available at https://github.com/ mapooon/BlendFace.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.10854")
get_code_for_paper("2307.10854")
have("2307.10854")

Connect an agent — have() is free.