Recent Progress of Face Image Synthesis

Lu, Zhihe; Li, Zhihang; Cao, Jie; He, Ran; Sun, Zhenan

doi:10.1109/acpr.2017.2

Cited by 19 publications

(13 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While GANs have made their mark on face synthesis research, other deep feature based techniques have been explored by researchers for reconstructing a face image [15,59,8,23,27]. A more detailed bibliography can be found in [41].…”

Section: Related Workmentioning

confidence: 99%

“…Face image synthesis has been a popular research area recently [41], mainly as a means to generate artificial training samples for CNNs [38]. Generative adversarial nets (GANs) [21] have made tremendous progress in this domain with different GAN models being used to generate synthetic face images with different pose [58,9,68], facial feature [52,10,60,67], age [20,3] and expression [39].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Face Image Synthesis With Minimal Training

Banerjee

Scheirer

Bowyer

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We propose an algorithm to generate realistic face images of both real and synthetic identities (people who do not exist) with different facial yaw, shape and resolution. The synthesized images can be used to augment datasets to train CNNs or as massive distractor sets for biometric verification experiments without any privacy concerns. Additionally, law enforcement can make use of this technique to train forensic experts to recognize faces. Our method samples face components from a pool of multiple face images of real identities to generate the synthetic texture. Then, a real 3D head model compatible to the generated texture is used to render it under different facial yaw transformations. We perform multiple quantitative experiments to assess the effectiveness of our synthesis procedure in CNN training and its potential use to generate distractor face images. Additionally, we compare our method with popular GAN models in terms of visual quality and execution time.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast Face Image Synthesis With Minimal Training

Banerjee

Scheirer

Bowyer

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Subjects appear in diverse events and activities, resulting in varied backgrounds and head poses. Meanwhile, current generative face models are limited to frontal [2] or strictly aligned faces [11].…”

Section: Introductionmentioning

confidence: 99%

Natural and Effective Obfuscation by Head Inpainting

Sun

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

188

144

View full text Add to dashboard Cite

As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection. People have largely resorted to blacking out or blurring head regions, but they result in poor user experience while being surprisingly ineffective against state of the art person recognizers [16]. In this work, we propose a novel head inpainting obfuscation technique. Generating a realistic head inpainting in social media photos is challenging because subjects appear in diverse activities and head orientations. We thus split the task into two sub-tasks: (1) facial landmark generation from image context (e.g. body pose) for seamless hypothesis of sensible head pose, and (2) facial landmark conditioned head inpainting. We verify that our inpainting method generates realistic person images, while achieving superior obfuscation performance against automatic person recognizers.

show abstract

“…An existing geometrical approach to facial image editing / synthesis involves modeling facial key points, texture, shape and other graphical characteristics, and can be used to model facial expressions directly [6]. This approach has been effectively used for facial image synthesis to increase subject diversity [7].…”

Section: Introductionmentioning

confidence: 99%

“…Current GAN-based facial editing can be employed on general facial attributes such as facial age [12], head pose [13], etc. [6], while AU-level expression editing with GAN has also been proposed in [14]. However, simply relying on GAN models to implicitly disentangle and manipulate discriminative expression descriptors from other facial attributes has met with limited success, with the generated facial images typically of low resolution, with difficulty in depicting differences due to AUs of varying intensities.…”

Section: Introductionmentioning

confidence: 99%

Conditional adversarial synthesis of 3D facial action units

et al. 2019

View full text Add to dashboard Cite

Employing deep learning-based approaches for finegrained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training. In this paper, we consider how AU-level facial image synthesis can be used to substantially augment such a dataset. We propose an AU synthesis framework that combines the well-known 3D Morphable Model (3DMM), which intrinsically disentangles expression parameters from other face attributes, with models that adversarially generate 3DMM expression parameters conditioned on given target AU labels, in contrast to the more conventional approach of generating facial images directly. In this way, we are able to synthesize new combinations of expression parameters and facial images from desired AU labels. Extensive quantitative and qualitative results on the benchmark DISFA dataset demonstrate the effectiveness of our method on 3DMM facial expression parameter synthesis and data augmentation for deep learning-based AU intensity estimation.

show abstract

Recent Progress of Face Image Synthesis

Cited by 19 publications

References 79 publications

Fast Face Image Synthesis With Minimal Training

Fast Face Image Synthesis With Minimal Training

Natural and Effective Obfuscation by Head Inpainting

Conditional adversarial synthesis of 3D facial action units

Contact Info

Product

Resources

About