Skip to search formSkip to main contentSkip to account menu
Interpreting the Latent Space of GANs for Semantic Face Editing
TLDR
This work proposes a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs, and finds that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations.
View on IEEE
In-Domain GAN Inversion for Real Image Editing
TLDR
An in-domain GAN inversion approach, which not only faithfully reconstructs the input image but also ensures the inverted code to be semantically meaningful for editing, which achieves satisfying real image reconstruction and facilitates various image editing tasks, significantly outperforming start-of-the-arts.
View PDF on arXiv
Closed-Form Factorization of Latent Semantics in GANs
TLDR
This work examines the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner and proposes a closedform factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
View on IEEE
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
TLDR
A framework called InterFaceGAN is proposed to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space to suggest that learning to synthesize faces spontaneously brings a disentangling and controllable face representation.
View on IEEE
Image Processing Using Multi-Code GAN Prior
TLDR
A novel approach is proposed, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks, by employing multiple latent codes to generate multiple feature maps at some intermediate layer of the generator and composing them with adaptive channel importance to recover the input image.
View on IEEE
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
TLDR
FaceID-GAN is able to generate faces of arbitrary viewpoint while preserve identity, outperforming recent advanced approaches and substantially alleviating training difficulty of GAN.
View on IEEE
Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
TLDR
This work shows that highly-structured semantic hierarchy emerges as variation factors from synthesizing scenes from the generative representations in state-of-the-art GAN models, like StyleGAN and BigGAN, and quantifies the causality between the activations and semantics occurring in the output image.
View PDF on arXiv
Generative Hierarchical Features from Synthesizing Images
TLDR
This work considers the pre-trained StyleGAN generator as a learned loss function and utilizes its layer-wise representation to train a novel hierarchical encoder, termed as Generative Hierarchical Feature (GH-Feat), which has strong transferability to both generative and discriminative tasks.
View on IEEE
Glancing at the Patch: Anomaly Localization with Global and Local Feature Comparison
TLDR
This work proposes an unsupervised patch-based approach that gives due consideration to both the global and local information in anomaly localization, and employs a Local-Net and Global-Net to extract features from any individual patch and its surrounding respectively.
View on IEEE
Improving the Fairness of Deep Generative Models without Retraining
TLDR
This work proposes a simple yet effective method to improve the fairness of image generation for a pre-trained GAN model without retraining and learns a Gaussian Mixture Model to fit a distribution of the latent code set, which supports the sampling of latent codes for producing images with a more fair attribute distribution.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License