UP-FacE: User-predictable Fine-grained Face Shape Editing

TL;DR

UP-FacE introduces a face editing method that allows users to predictably and precisely control face shape modifications using facial landmarks and a transformer-based model, enabling fine-grained editing without manual labels.

Contribution

The paper presents a novel face editing approach that offers deterministic control over shape changes, leveraging facial landmarks and a transformer network without requiring manual attribute annotations.

Findings

Enables precise control over 23 face shape features.

Uses facial landmarks for accurate feature measurement.

Achieves high-quality, predictable face shape editing.

Abstract

We present User-predictable Face Editing (UP-FacE) -- a novel method for predictable face shape editing. In stark contrast to existing methods for face editing using trial and error, edits with UP-FacE are predictable by the human user. That is, users can control the desired degree of change precisely and deterministically and know upfront the amount of change required to achieve a certain editing result. Our method leverages facial landmarks to precisely measure facial feature values, facilitating the training of UP-FacE without manually annotated attribute labels. At the core of UP-FacE is a transformer-based network that takes as input a latent vector from a pre-trained generative model and a facial feature embedding, and predicts a suitable manipulation vector. To enable user-predictable editing, a scaling layer adjusts the manipulation vector to achieve the precise desired degree of change. To ensure that the desired feature is manipulated towards the target value without altering uncorrelated features, we further introduce a novel semantic face feature loss. Qualitative and quantitative results demonstrate that UP-FacE enables precise and fine-grained control over 23 face shape features.