BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network

Chen, Hung‐Jen; Hui, K.; Wang, Szu-Yu; Tsao, Li-Wu; Shuai, Hong-Han; Cheng, Wen-Huang

doi:10.1109/cvpr.2019.01028

Cited by 87 publications

(73 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two input features, z t−1 and z t+1 , are predicted from the image encoder. One can fuse the features by averaging them, similarly with image morphing or style transfer approach [31]. However, the ensemble of features may lose detailed structures because two sequential frames can be misaligned owning to local motions of dynamic objects and global motions.…”

Section: ) Latent Encodermentioning

confidence: 99%

Direct Video Frame Interpolation With Multiple Latent Encoders

2021

View full text Add to dashboard Cite

We present a simple but effective video interpolation framework that can be applied to various types of videos including conventional videos and 360 • videos. Our main idea is to predict the latent feature of an intermediate frame, through the latent feature encoders between encoder and decoder networks, without explicitly computing optical flow or depth maps. The latent feature encoders take latent features of input images and then predict the latent feature of a target image, i.e. an intermediate frame. Afterward, the decoder network reconstructs the target image from the latent feature. The proposed framework consists of fully convolutional networks, and it is therefore end-to-end trainable from scratch without requiring additional information except for consecutive frames. We experimentally verify the superiority of proposed method by comparing it to state-of-the-art methods with various types of datasets. Moreover, an ablation study is carried out to analyze the key components of the proposed method. Our proposed method performs interpolation in latent domain, it is advantageous to apply various video interpolation (e.g. NIR and depth videos) without limiting the type of input data. INDEX TERMSVideo interpolation, 360 • video interpolation, latent space learning, convolutional neural network VOLUME XX, 2020This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2021.3053695, IEEE Access Direct Video Frame Interpolation with Multiple Latent EncodersFIGURE 4. Network architecture of the image encoder, latent encoder, and latent decoder. Here, k, n, and s denote the convolution kernel size, the number of filter maps, and the stride, respectively.

show abstract

Section: ) Latent Encodermentioning

confidence: 99%

Direct Video Frame Interpolation With Multiple Latent Encoders

2021

View full text Add to dashboard Cite

show abstract

“…In addition, we also used some images synthesized using a deep learning-based generative network known as Beauty-Glow [40]. The generative network performs a style transfer on the makeup of the individual in face images, resulting in nearduplicates as shown in Figure 8(a).…”

Section: Experiments 7: Ability To Handle Deep Learning-based Transformentioning

confidence: 99%

Face Phylogeny Tree Using Basis Functions

Banerjee

Ross

2020

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Photometric transformations, such as brightness and contrast adjustment, can be applied to a face image repeatedly creating a set of near-duplicate images. Identifying the original image from a set of such near-duplicates and deducing the relationship between them are important in the context of digital image forensics. This is commonly done by generating an image phylogeny treea hierarchical structure depicting the relationship between a set of near-duplicate images. In this work, we utilize three different families of basis functions to model pairwise relationships between near-duplicate images. The basis functions used in this work are orthogonal polynomials, wavelet basis functions and radial basis functions. We perform extensive experiments to assess the performance of the proposed method across three different modalities, namely, face, fingerprint and iris images; across different image phylogeny tree configurations; and across different types of photometric transformations. We also utilize the same basis functions to model geometric transformations and deep-learning based transformations. We also perform extensive analysis of each basis function with respect to its ability to model arbitrary transformations and to distinguish between the original and the transformed images. Finally, we utilize the concept of approximate von Neumann graph entropy to explain the success and failure cases of the proposed IPT generation algorithm. Experiments indicate that the proposed algorithm generalizes well across different scenarios thereby suggesting the merits of using basis functions to model the relationship between photometrically and geometrically modified images. !• Both the authors are with the

show abstract

“…Chen et al [17] also proposed a method for unpaired image-to-image translation that based on latent space interpolation. Chen et al [18] applied a reversible generative network based framework for makeup transfer, which can also be seen as an image-to-image translation task.…”

Section: B Image-to-image Translationmentioning

confidence: 99%

ResAttr-GAN: Unpaired Deep Residual Attributes Learning for Multi-Domain Face Image Translation

Tao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Facial attributes edit can be seen as an image-to-image translation problem, whose goal is to transfer images from the source domain to the target domain. Specially, facial attributes edit aims at changing some semantic attributes of a given face image while keeping the contents of unrelated area unchanged. The great challenge for this problem lies on the lacking of paired data, i.e. we do not have paired face images that only differ on particular attributes. Moreover, to train a good attributes editing model, there always needs a great amount of train data which labeled by hand. If the train data amount was reduced, then the editing performance would decrease accordingly. Strong intelligent systems should be able to learn knowledge from less data samples (similar idea with few-shot learning). To mitigate this limitation, in this paper, we proposed a Siamese-Network based residual attributes learning model to learn the attributes difference in the high-level latent space. Compared to existing models that perform attributes editing based on an attributes classifier, the proposed deep residual attributes learning model utilized relatively weaker information of attribute differences for face image translation. Sufficient qualitative and quantitative experiments conducted on CelebA dataset proved the effectiveness of our proposed method, moreover, we also adopt the proposed residual attributes learning model in two state-of-the-art models under different data usage percentage to show the effectiveness of the proposed model on boosting attribute editing performance under limited data usage. The experiment results proved that the proposed method can improve data utilization efficiency and thus can boost the editing performance when the train data was limited. INDEX TERMS Facial attributes edit, image-to-image translation, generative adversarial network, residual attributes learning.

show abstract

BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network

Cited by 87 publications

References 19 publications

Direct Video Frame Interpolation With Multiple Latent Encoders

Direct Video Frame Interpolation With Multiple Latent Encoders

Face Phylogeny Tree Using Basis Functions

ResAttr-GAN: Unpaired Deep Residual Attributes Learning for Multi-Domain Face Image Translation

Contact Info

Product

Resources

About