As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …

Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in
various image generation tasks compared with Generative Adversarial Nets (GANs). Recent …

Typical layout-to-image synthesis (LIS) models generate images for a closed set of semantic
classes, eg, 182 common objects in COCO-Stuff. In this work, we explore the freestyle …

Despite the great success of GANs in images translation with different conditioned inputs
such as semantic segmentation and edge map, generating high-fidelity images with …

Despite their recent successes, GAN models for semantic image synthesis still suffer from
poor image quality when trained with only adversarial supervision. Historically, additionally …

Exemplar-based image translation establishes dense correspondences between a
conditional input and an exemplar (from two different domains) for leveraging detailed …

Deep generative models have achieved conspicuous progress in realistic image synthesis
with multifarious conditional inputs, while generating diverse yet high-fidelity images …

Illumination estimation from a single image is critical in 3D rendering and it has been
investigated extensively in the computer vision and computer graphic research community …

Recent studies have shown that StyleGANs provide promising prior models for downstream
tasks on image synthesis and editing. However, since the latent codes of StyleGANs are …