
TL;DR
MFIM introduces a high-quality, megapixel face-swapping framework that leverages pretrained StyleGAN and 3DMM for effective identity transformation and offers a novel ID mixing operation for customizable identities.
Contribution
The paper presents a novel face-swapping method that generates megapixel images using StyleGAN and 3DMM supervision, with a new ID mixing operation for identity customization.
Findings
Achieves state-of-the-art face swapping quality.
Effectively transforms facial identity attributes.
Enables customizable identity creation through ID mixing.
Abstract
Face swapping is a task that changes a facial identity of a given image to that of another person. In this work, we propose a novel face-swapping framework called Megapixel Facial Identity Manipulation (MFIM). The face-swapping model should achieve two goals. First, it should be able to generate a high-quality image. We argue that a model which is proficient in generating a megapixel image can achieve this goal. However, generating a megapixel image is generally difficult without careful model design. Therefore, our model exploits pretrained StyleGAN in the manner of GAN-inversion to effectively generate a megapixel image. Second, it should be able to effectively transform the identity of a given image. Specifically, it should be able to actively transform ID attributes (e.g., face shape and eyes) of a given image into those of another person, while preserving ID-irrelevant attributes…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsHuMan(Expedia)||How do I get a human at Expedia? · Adaptive Instance Normalization · R1 Regularization · Dense Connections · Convolution · Feedforward Network · StyleGAN
