paper-with-me

홈 › Papers

Contrastive Learning for Diverse Disentangled Foreground Generation

2022-11-04 · Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh

We introduce a new method for diverse foreground generation with explicit control over various factors. Existing image inpainting based foreground generation methods often struggle to generate diverse results and rarely allow users to explicitly control specific factors of variation (e.g., varying the facial identity or expression for face inpainting results). We leverage contrastive learning with latent codes to generate diverse foreground results for the same masked input. Specifically, we define two sets of latent codes, where one controls a pre-defined factor (`known''), and the other controls the remaining factors (`unknown''). The sampled latent codes from the two sets jointly bi-modulate the convolution kernels to guide the generator to synthesize diverse results. Experiments demonstrate the superiority of our method over state-of-the-arts in result diversity and generation controllability.

📄 PDF Abstract BibTeX arXiv:2211.02707

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningDiversityFacial InpaintingImage Inpainting

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Attribute2Image: Conditional Image Generation from Visual Attributes

2015-12-02 · Xinchen Yan, Jimei Yang, Kihyuk Sohn, Honglak Lee

This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variable…

AttributeConditional Image GenerationImage GenerationImage Reconstruction

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 외

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. W…

Contrastive LearningDisentanglementImage Generation

Disentangled Person Image Generation

2017-12-07 · CVPR 2018 6 · Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc van Gool 외

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at …

Gesture-to-Gesture TranslationImage GenerationPerson Re-IdentificationPose Transfer

Disentangled Contrastive Image Translation for Nighttime Surveillance

2023-07-11 · Guanzhou Lan, Bin Zhao, Xuelong Li

Nighttime surveillance suffers from degradation due to poor illumination and arduous human annotations. It is challengable and remains a security risk at night. Existing methods rely on multi-spectral images to perceive …

Contrastive LearningTranslation

DualVAE: Dual Disentangled Variational AutoEncoder for Recommendation

2024-01-10 · Zhiqiang Guo, GuoHui Li, Jianjun Li, Chaoyang Wang 외

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction da…

Collaborative FilteringDisentanglementRepresentation LearningVariational Inference