# SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters

arXiv: https://arxiv.org/abs/1908.09638 · HTML: https://mlsanity.com/paper/1908.09638/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [3D-FM GAN: Towards 3D-Controllable Face Manipulation](https://mlsanity.com/paper/2208.11257/) (2022)
- [3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views](https://mlsanity.com/paper/2212.02997/) (2022)
- [Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation](https://mlsanity.com/paper/2504.05672/) (2025)
- [Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing](https://mlsanity.com/paper/2103.02854/) (2021)
- [Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape](https://mlsanity.com/paper/2310.20240/) (2023)
- [F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks](https://mlsanity.com/paper/2205.06204/) (2022)
- [Talking Head(?) Anime from a Single Image 4: Improved Model and Its Distillation](https://mlsanity.com/paper/2311.17409/) (2023)
- [CharGen: Fast and Fluent Portrait Modification](https://mlsanity.com/paper/2509.25058/) (2025)
- [Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction](https://mlsanity.com/paper/2605.09697/) (2026)

## Abstract (arXiv)

Image-to-image (i2i) translation is the dense regression problem of learning how to transform an input image into an output using aligned image pairs. Remarkable progress has been made in i2i translation with the advent of Deep Convolutional Neural Networks (DCNNs) and particular using the learning paradigm of Generative Adversarial Networks (GANs). In the absence of paired images, i2i translation is tackled with one or multiple domain transformations (i.e., CycleGAN, StarGAN etc.). In this paper, we study a new problem, that of image-to-image translation, under a set of continuous parameters that correspond to a model describing a physical process. In particular, we propose the SliderGAN which transforms an input face image into a new one according to the continuous values of a statistical blendshape model of facial motion. We show that it is possible to edit a facial image according to expression and speech blendshapes, using sliders that control the continuous values of the blendshape model. This provides much more flexibility in various tasks, including but not limited to face editing, expression transfer and face neutralisation, comparing to models based on discrete expressions or action units.