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.

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Latest papers with code

Face Manifold: Manifold Learning for Synthetic Face Generation

3 Oct 2019SCL-UT/face-manifold

The main challenge of such techniques is a vital need for large 3D face datasets.

3D FACE RECONSTRUCTION DENOISING FACE GENERATION FACE RECOGNITION

8
03 Oct 2019

Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks

5 Sep 2019barisgecer/TBGAN

In this paper, we present the first methodology that generates high-quality texture, shape, and normals jointly, which can be used for photo-realistic synthesis.

FACE GENERATION

45
05 Sep 2019

Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss

CVPR 2019 lelechen63/ATVGnet

We devise a cascade GAN approach to generate talking face video, which is robust to different face shapes, view angles, facial characteristics, and noisy audio conditions.

TALKING FACE GENERATION

75
01 Jun 2019

Unsupervised Face Normalization With Extreme Pose and Expression in the Wild

CVPR 2019 mx54039q/fnm

Face normalization provides an effective and cheap way to distil face identity and dispel face variances for recognition.

FACE GENERATION FACE RECOGNITION

50
01 Jun 2019

COCO-GAN: Generation by Parts via Conditional Coordinating

30 Mar 2019hubert0527/COCO-GAN

Despite the full images are never generated during training, we show that COCO-GAN can produce \textbf{state-of-the-art-quality} full images during inference.

FACE GENERATION

111
30 Mar 2019

Photo-Realistic Facial Details Synthesis from Single Image

26 Mar 2019apchenstu/Facial_Details_Synthesis

Our technique employs expression analysis for proxy face geometry generation and combines supervised and unsupervised learning for facial detail synthesis.

FACE GENERATION

259
26 Mar 2019

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

19 Dec 2018human-analysis/RankGAN

We present a new stage-wise learning paradigm for training generative adversarial networks (GANs).

FACE GENERATION

7
19 Dec 2018

Triple consistency loss for pairing distributions in GAN-based face synthesis

8 Nov 2018ESanchezLozano/GANnotation

To show this is effective, we incorporate the triple consistency loss into the training of a new landmark-guided face to face synthesis, where, contrary to previous works, the generated images can simultaneously undergo a large transformation in both expression and pose.

FACE GENERATION

94
08 Nov 2018

Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition

2 Sep 2018ZhaoJ9014/High_Performance_Face_Recognition

Benchmarking our model on one of the most popular unconstrained face recognition datasets IJB-C additionally verifies the promising generalizability of AIM in recognizing faces in the wild.

AGE-INVARIANT FACE RECOGNITION BENCHMARKING FACE GENERATION REPRESENTATION LEARNING

250
02 Sep 2018

Everybody Dance Now

22 Aug 2018Lotayou/everybody_dance_now_pytorch

This paper presents a simple method for "do as I do" motion transfer: given a source video of a person dancing, we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard moves.

FACE GENERATION IMAGE-TO-IMAGE TRANSLATION VIDEO GENERATION

115
22 Aug 2018