ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes

Xiao, Taihong; Hong, Jiapeng; Ma, Jinwen

doi:10.48550/arxiv.1803.10562

Cited by 10 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11, we show additional visual results of attribute transfer for specific attribute: Smiling. We compare our MaskGAN with state-of-the art methods including Pix2PixHD [27] with modification, ELEGANT [29], and StarGAN [2].…”

Section: B Additional Visual Resultsmentioning

confidence: 99%

“…Some recent studies [30,29,31] start to discuss the possibility of transferring facial at instance level from exemplars. For example, ELEGANT [29] was proposed to exchange attribute between two faces by exchanging the latent codes of two faces. However, ELEGANT [29] cannot transfer the attribute (e.g.…”

Section: Related Workmentioning

confidence: 99%

“…For example, ELEGANT [29] was proposed to exchange attribute between two faces by exchanging the latent codes of two faces. However, ELEGANT [29] cannot transfer the attribute (e.g. 'smiling') from exemplars accurately.…”

Section: Related Workmentioning

confidence: 99%

“…Competing Methods. We choose state-of-the-art StarGAN [2], ELEGANT [29] and Pix2PixHD [27] as our baselines.…”

Section: Datasetsmentioning

confidence: 99%

“…hair style, skin color) transfer. This task can be roughly categorized into two types: semantic-level manipulation [2,17,21,14,16] and geometry-level manipulation [30,29,31]. However, these methods either operate on a pre-defined set of attributes or leave users little freedom to interactively manipulate the face images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

Lee¹,

Liu

Wu³

et al. 2019

Preprint

View full text Add to dashboard Cite

Facial image manipulation has achieved great progresses in recent years. However, previous methods either operate on a predefined set of face attributes or leave users little freedom to interactively manipulate images. To overcome these drawbacks, we propose a novel framework termed MaskGAN, enabling diverse and interactive face manipulation. Our key insight is that semantic masks serve as a suitable intermediate representation for flexible face manipulation with fidelity preservation. MaskGAN has two main components: 1) Dense Mapping Network, and 2) Editing Behavior Simulated Training. Specifically, Dense mapping network learns style mapping between a free-form user modified mask and a target image, enabling diverse generation results. Editing behavior simulated training models the user editing behavior on the source mask, making the overall framework more robust to various manipulated inputs. To facilitate extensive studies, we construct a large-scale high-resolution face dataset with fine-grained mask annotations named CelebAMask-HQ. MaskGAN is comprehensively evaluated on two chal-lenging tasks: attribute transfer and style copy, demonstrating superior performance over other state-of-the-art methods. The code, models and dataset are available at https://github.com/switchablenorms/CelebAMask-HQ.

show abstract

Section: B Additional Visual Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Competing Methods. We choose state-of-the-art StarGAN [2], ELEGANT [29] and Pix2PixHD [27] as our baselines.…”

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

Lee¹,

Liu

Wu³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

Bozorgtabar

Rad

Ekenel

et al. 2019

2019 14th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2019)

View full text Add to dashboard Cite

Cross-domain synthesizing realistic faces to learn deep models has attracted increasing attention for facial expression analysis as it helps to improve the performance of expression recognition accuracy despite having small number of real training images. However, learning from synthetic face images can be problematic due to the distribution discrepancy between low-quality synthetic images and real face images and may not achieve the desired performance when the learned model applies to real world scenarios. To this end, we propose a new attribute guided face image synthesis to perform a translation between multiple image domains using a single model. In addition, we adopt the proposed model to learn from synthetic faces by matching the feature distributions between different domains while preserving each domain's characteristics. We evaluate the effectiveness of the proposed approach on several face datasets on generating realistic face images. We demonstrate that the expression recognition performance can be enhanced by benefiting from our face synthesis model. Moreover, we also conduct experiments on a near-infrared dataset containing facial expression videos of drivers to assess the performance using in-the-wild data for driver emotion recognition.

show abstract

Sparsely Grouped Multi-Task Generative Adversarial Networks for Facial Attribute Manipulation

Zhang

Shu

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Recently, Image-to-Image Translation (IIT) has achieved great progress in image style transfer and semantic context manipulation for images. However, existing approaches require exhaustively labelling training data, which is labor demanding, difficult to scale up, and hard to adapt to a new domain. To overcome such a key limitation, we propose Sparsely Grouped Generative Adversarial Networks (SG-GAN) as a novel approach that can translate images in sparsely grouped datasets where only a few train samples are labelled. Using a one-input multi-output architecture, SG-GAN is well-suited for tackling multi-task learning and sparsely grouped learning tasks. The new model is able to translate images among multiple groups using only a single trained model. To experimentally validate the advantages of the new model, we apply the proposed method to tackle a series of attribute manipulation tasks for facial images as a case study. Experimental results show that SG-GAN can achieve comparable results with state-of-the-art methods on adequately labelled datasets while attaining a superior image translation quality on sparsely grouped datasets 1 .

show abstract

ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes

Cited by 10 publications

References 16 publications

MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

Sparsely Grouped Multi-Task Generative Adversarial Networks for Facial Attribute Manipulation

Contact Info

Product

Resources

About