68 citations · 83 across the 5 of their papers we have counts for
7 papers
AutoDecoding Latent 3D Diffusion Models
Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski +3
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from…
StyleGenes: Discrete and Efficient Latent Distributions for GANs
Evangelos Ntavelis, Mohamad Shahbazi, Iason Kastanis +3
We propose a discrete latent distribution for Generative Adversarial Networks (GANs). Instead of drawing latent vectors from a continuous prior, we sample from a finite set of lear…
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Mohamad Shahbazi, Evangelos Ntavelis, Alessio Tonioni +4
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors. Rec…
Arbitrary-Scale Image Synthesis
Evangelos Ntavelis, Mohamad Shahbazi, Iason Kastanis +3
Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a…
SkyCam: A Dataset of Sky Images and their Irradiance values
Evangelos Ntavelis, Jan Remund, Philipp Schmid
Recent advances in Computer Vision and Deep Learning have enabled astonishing results in a variety of fields and applications. Motivated by this success, the SkyCam Dataset aims to…
AIM 2020 Challenge on Image Extreme Inpainting
Evangelos Ntavelis, Andrés Romero, Siavash Bigdeli +1
This paper reviews the AIM 2020 challenge on extreme image inpainting. This report focuses on proposed solutions and results for two different tracks on extreme image inpainting: c…
SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
Evangelos Ntavelis, Andrés Romero, Iason Kastanis +2
Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundanc…