paper-with-me

Papers

Wasserstein Loss for Semantic Editing in the Latent Space of GANs

2023-03-22 · Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne

The latent space of GANs contains rich semantics reflecting the training data. Different methods propose to learn edits in latent space corresponding to semantic attributes, thus allowing to modify generated images. Most supervised methods rely on the guidance of classifiers to produce such edits. However, classifiers can lead to out-of-distribution regions and be fooled by adversarial samples. We propose an alternative formulation based on the Wasserstein loss that avoids such problems, while maintaining performance on-par with classifier-based approaches. We demonstrate the effectiveness of our method on two datasets (digits and faces) using StyleGAN2.

📄 PDF Abstract BibTeX arXiv:2304.10508

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Path Length Regularization 설명 없음
Weight Demodulation 설명 없음
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…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…

Similar Papers 제목 키워드 기반

Image-to-Image Translation with Disentangled Latent Vectors for Face Editing

2023-01-11 · Yusuf Dalva, Hamza Pehlivan, Cansu Moran, Öykü Irmak Hatipoğlu 외

We propose an image-to-image translation framework for facial attribute editing with disentangled interpretable latent directions. Facial attribute editing task faces the challenges of targeted attribute editing with con…

AttributeDecoderDisentanglementImage-to-Image Translation+1

Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation

2021-02-01 · ICLR 2021 1 · Peiye Zhuang, Oluwasanmi Koyejo, Alexander G. Schwing

Controllable semantic image editing enables a user to change entire image attributes with a few clicks, e.g., gradually making a summer scene look like it was taken in winter. Classic approaches for this task use a Gener…

AttributeImage Manipulation

Towards Counterfactual Image Manipulation via CLIP

2022-07-06 · Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jiahui Zhang 외

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging p…

counterfactualImage Manipulation

Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic Editing

2024-11-12 · Zitao Shuai, Chenwei Wu, Zhengxu Tang, Bowen Song 외

Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize…

DisentanglementImage Generation

GAN Inversion for Out-of-Range Images with Geometric Transformations

2021-08-20 · ICCV 2021 10 · Kyoungkook Kang, Seongtae Kim, Sunghyun Cho

For successful semantic editing of real images, it is critical for a GAN inversion method to find an in-domain latent code that aligns with the domain of a pre-trained GAN model. Unfortunately, such in-domain latent code…