paper-with-me

Papers

Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning

2020-04-24 · CVPR 2020 6 · Yu Deng, Jiaolong Yang, Dong Chen, Fang Wen, Xin Tong

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.

📄 PDF Abstract BibTeX arXiv:2004.11660

Code (4)

microsoft/DisentangledFaceGAN 공식 구현 tf
microsoft/DiscoFaceGAN tf
mk-minchul/cse802_face_augmentation pytorch
pengfudan/DisentangledFaceGAN tf

Tasks

Contrastive LearningDisentanglementImage Generation

Similar Papers 제목 키워드 기반

Semi-Supervised StyleGAN for Disentanglement Learning

2020-03-06 · ICML 2020 1 · Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath 외

Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, prima…

DisentanglementRepresentation Learning

Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Control

2024-04-24 · Linzi Qu, Jiaxiang Shang, Hui Ye, Xiaoguang Han 외

Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking …

Face GenerationImage Generation

Content-style disentangled representation for controllable artistic image stylization and generation

2024-12-19 · Ma Zhuoqi, Zhang Yixuan, You Zejun, Tian Long 외

Controllable artistic image stylization and generation aims to render the content provided by text or image with the learned artistic style, where content and style decoupling is the key to achieve satisfactory results. …

DisentanglementImage Stylization

Disentangled GANs for Controllable Generation of High-Resolution Images

2019-09-25 · Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debhath 외

Generative adversarial networks (GANs) have achieved great success at generating realistic samples. However, achieving disentangled and controllable generation still remains challenging for GANs, especially in the high-r…

DisentanglementVocal Bursts Intensity Prediction

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

2024-12-25 · Enbo Huang, Yuan Zhang, Faliang Huang, Guangyu Zhang 외

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face s…

Image GenerationPose TransferVirtual Try-on