Diffusion self-guidance for controllable image generation
Large-scale generative models are capable of producing high-quality images from detailed
prompts. However, many aspects of an image are difficult or impossible to convey through …
prompts. However, many aspects of an image are difficult or impossible to convey through …
Survey on leveraging pre-trained generative adversarial networks for image editing and restoration
Generative adversarial networks (GANs) have drawn enormous attention due to their simple
yet effective training mechanism and superior image generation quality. With the ability to …
yet effective training mechanism and superior image generation quality. With the ability to …
Blobgan: Spatially disentangled scene representations
We propose an unsupervised, mid-level representation for a generative model of scenes.
The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes …
The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes …
Linkgan: Linking gan latents to pixels for controllable image synthesis
This work presents an easy-to-use regularizer for GAN training, which helps explicitly link
some axes of the latent space to a set of pixels in the synthesized image. Establishing such …
some axes of the latent space to a set of pixels in the synthesized image. Establishing such …
Householder projector for unsupervised latent semantics discovery
Abstract Generative Adversarial Networks (GANs), especially the recent style-based
generators (StyleGANs), have versatile semantics in the structured latent space. Latent …
generators (StyleGANs), have versatile semantics in the structured latent space. Latent …
High-fidelity gan inversion with padding space
Abstract Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image
editing tasks using pre-trained generators. Existing methods typically employ the latent …
editing tasks using pre-trained generators. Existing methods typically employ the latent …
Flow factorized representation learning
A prominent goal of representation learning research is to achieve representations which
are factorized in a useful manner with respect to the ground truth factors of variation. The …
are factorized in a useful manner with respect to the ground truth factors of variation. The …
Bilinear models of parts and appearances in generative adversarial networks
Recent advances in the understanding of Generative Adversarial Networks (GANs) have led
to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich …
to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich …
Panda: Unsupervised learning of parts and appearances in the feature maps of gans
Recent advances in the understanding of Generative Adversarial Networks (GANs) have led
to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich …
to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich …
Exploring sparse moe in gans for text-conditioned image synthesis
Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling
from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of …
from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of …