Face generation is the task of generating (or interpolating) new faces from an existing dataset.

The state-of-the-art results for this task are located in the Image Generation parent.

( Image credit: Progressive Growing of GANs for Improved Quality, Stability, and Variation )

Leaderboards

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Latest papers without code

Identity-Preserving Realistic Talking Face Generation

25 May 2020

The necessary attributes of having a realistic face animation are 1) audio-visual synchronization (2) identity preservation of the target individual (3) plausible mouth movements (4) presence of natural eye blinks.

AUDIO-VISUAL SYNCHRONIZATION IMAGE RECONSTRUCTION TALKING FACE GENERATION

InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs

18 May 2020

Finally, we apply our approach to real face editing by involving GAN inversion approaches as well as explicitly training additional feed-forward models based on the synthetic data established by InterFaceGAN.

FACE GENERATION

One-Shot Domain Adaptation For Face Generation

28 Mar 2020

To generate images of the same distribution, we introduce a style-mixing technique that transfers the low-level statistics from the target to faces randomly generated with the model.

DOMAIN ADAPTATION FACE GENERATION

Controllable Descendant Face Synthesis

26 Feb 2020

Most of the existing methods train models for one-versus-one kin relation, which only consider one parent face and one child face by directly using an auto-encoder without any explicit control over the resemblance of the synthesized face to the parent face.

FACE GENERATION

FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles

27 Jan 2020

Although many methods focus on fake detection, only a few put emphasis on the localization of the fake regions.

FACE GENERATION SEMANTIC SEGMENTATION

Is There Mode Collapse? A Case Study on Face Generation and Its Black-box Calibration

ICLR 2020

Generative adversarial networks (GANs) nowadays are capable of producing im-ages of incredible realism.

CALIBRATION FACE GENERATION

DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

1 Jan 2020

The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake content with its corresponding implications towards society in this era of fake news.

DEEPFAKE DETECTION FACE GENERATION FACE SWAPPING

PI-GAN: Learning Pose Independent representations for multiple profile face synthesis

26 Dec 2019

Generating a pose-invariant representation capable of synthesizing multiple face pose views from a single pose is still a difficult problem.

FACE GENERATION

Facial Synthesis from Visual Attributes via Sketch using Multi-Scale Generators

17 Dec 2019

In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.

FACE GENERATION

What Will Your Child Look Like? DNA-Net: Age and Gender Aware Kin Face Synthesizer

16 Nov 2019

Specifically, we propose a two-stage kin-face generation model to predict the appearance of a child given a pair of parents.

FACE GENERATION