Dual contrastive loss and attention for gans
Abstract Generative Adversarial Networks (GANs) produce impressive results on
unconditional image generation when powered with large-scale image datasets. Yet …
unconditional image generation when powered with large-scale image datasets. Yet …
Fair generative modeling via weak supervision
Real-world datasets are often biased with respect to key demographic factors such as race
and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias …
and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias …
On the convergence and robustness of training gans with regularized optimal transport
Abstract Generative Adversarial Networks (GANs) are one of the most practical methods for
learning data distributions. A popular GAN formulation is based on the use of Wasserstein …
learning data distributions. A popular GAN formulation is based on the use of Wasserstein …
Boundless: Generative adversarial networks for image extension
Image extension models have broad applications in image editing, computational
photography and computer graphics. While image inpainting has been extensively studied …
photography and computer graphics. While image inpainting has been extensively studied …
Logan: Latent optimisation for generative adversarial networks
Training generative adversarial networks requires balancing of delicate adversarial
dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with …
dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with …
Bootstrapping conditional gans for video game level generation
Generative Adversarial Networks (GANs) have shown impressive results for image
generation. However, GANs face challenges in generating contents with certain types of …
generation. However, GANs face challenges in generating contents with certain types of …
Object-centric image generation from layouts
We begin with the hypothesis that a model must be able to understand individual objects
and relationships between objects in order to generate complex scenes with multiple objects …
and relationships between objects in order to generate complex scenes with multiple objects …
Dranet: Disentangling representation and adaptation networks for unsupervised cross-domain adaptation
In this paper, we present DRANet, a network architecture that disentangles image
representations and transfers the visual attributes in a latent space for unsupervised cross …
representations and transfers the visual attributes in a latent space for unsupervised cross …
Lighthouse: Predicting lighting volumes for spatially-coherent illumination
We present a deep learning solution for estimating the incident illumination at any 3D
location within a scene from an input narrow-baseline stereo image pair. Previous …
location within a scene from an input narrow-baseline stereo image pair. Previous …
Learning canonical representations for scene graph to image generation
Generating realistic images of complex visual scenes becomes challenging when one
wishes to control the structure of the generated images. Previous approaches showed that …
wishes to control the structure of the generated images. Previous approaches showed that …