Pivotal Tuning for Latent-based Editing of Real Images
Open Access
- 12 August 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (1), 1-13
- https://doi.org/10.1145/3544777
Abstract
Recently, numerous facial editing techniques have been proposed that leverage the generative power of a pretrained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the pretrained generator’s domain. As it turns out, StyleGAN’s latent space induces an inherent tradeoff between distortion and editability, i.e., between maintaining the original appearance and convincingly altering its attributes. Hence, it remains challenging to apply ID-preserving edits to real facial images. In this paper, we present an approach to bridge this gap. The idea is pivotal tuning — a brief training process that preserves editing quality, while surgically changing the portrayed identity and appearance. In Pivotal Tuning Inversion (PTI), an initial inverted latent code serves as a pivot, around which the generator is fine-tuned. At the same time, a regularisation term keeps nearby identities intact, to locally contain the effect. We further show that pivotal tuning also applies to accommodating for a multitude of faces, while introducing negligible distortion on the rest of the domain. We validate our technique through inversion and editing metrics, and show preferable scores to state-of-the-art methods. Lastly, we present successful editing for harder cases, including elaborate make-up or headwearKeywords
This publication has 32 references indexed in Scilit:
- Semantic photo manipulation with a generative image priorACM Transactions on Graphics, 2019
- ArcFace: Additive Angular Margin Loss for Deep Face RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- A Style-Based Generator Architecture for Generative Adversarial NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Inverting the Generator of a Generative Adversarial NetworkIEEE Transactions on Neural Networks and Learning Systems, 2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual MetricPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Learning Inverse Mapping by AutoEncoder Based Generative Adversarial NetsPublished by Springer Science and Business Media LLC ,2017
- Generative Visual Manipulation on the Natural Image ManifoldPublished by Springer Science and Business Media LLC ,2016
- Deep Learning Face Attributes in the WildPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- 3D Object Representations for Fine-Grained CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Multiscale structural similarity for image quality assessmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004