Related papers: StyleFusion: A Generative Model for Disentangling …
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad…
We propose an efficient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs. Taking the StyleGAN trained on the FFHQ…
Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent…
Recent studies on StyleGAN variants show promising performances for various generation tasks. In these models, latent codes have traditionally been manipulated and searched for the desired images. However, this approach sometimes suffers…
Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of still images, as well as the learning of temporal correlations. However, few works manage to combine these two interesting capabilities for…
Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lacks of control over the generation process in order to…
The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the motion features in the…
One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. One challenging quality factor is the resolution of the output video: higher…
StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing…
Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…
While recent research has progressively overcome the low-resolution constraint of one-shot face video re-enactment with the help of StyleGAN's high-fidelity portrait generation, these approaches rely on at least one of the following:…
We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent…
Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial…
Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to…
Employing the latent space of pretrained generators has recently been shown to be an effective means for GAN-based face manipulation. The success of this approach heavily relies on the innate disentanglement of the latent space axes of the…
Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability…
Facial attributes in StyleGAN generated images are entangled in the latent space which makes it very difficult to independently control a specific attribute without affecting the others. Supervised attribute editing requires annotated…
We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs…
We introduce a method that allows to automatically segment images into semantically meaningful regions without human supervision. Derived regions are consistent across different images and coincide with human-defined semantic classes on…
Generative Adversarial Networks (GANs) can synthesize realistic images, with the learned latent space shown to encode rich semantic information with various interpretable directions. However, due to the unstructured nature of the learned…