Visual Emotion Analysis (VEA) aims at predicting people's emotional resp...
Denoising diffusion models have recently shown impressive results in
gen...
Editing a local region or a specific object in a 3D scene represented by...
Text-to-image model personalization aims to introduce a user-provided co...
Recent text-to-image diffusion models are able to generate convincing re...
How can one visually characterize people in a decade? In this work, we
a...
The tremendous progress in neural image generation, coupled with the
eme...
We introduce an unsupervised technique for encoding point clouds into a
...
Truncation is widely used in generative models for improving the quality...
StyleGAN is arguably one of the most intriguing and well-studied generat...
We present ShapeFormer, a transformer-based network that produces a
dist...
Natural language offers a highly intuitive interface for image editing. ...
In this paper, we perform an in-depth study of the properties and
applic...
RGB-D semantic segmentation has attracted increasing attention over the ...
Today's generative models are capable of synthesizing high-fidelity imag...
Inspired by the ability of StyleGAN to generate highly realistic images ...
Edge-preserving filters play an essential role in some of the most basic...
We explore and analyze the latent style space of StyleGAN2, a
state-of-t...
Capturing the 3D geometry of transparent objects is a challenging task,
...
We present an integrated approach for creating and assigning color palet...
We introduce MotioNet, a deep neural network that directly reconstructs ...
Convolutional layers are the core building blocks of Convolutional Neura...
Transferring the motion style from one animation clip to another, while
...
We introduce a novel deep learning framework for data-driven motion
reta...
The emergence of deep generative models has recently enabled the automat...
The emergence of generative models based on deep neural networks has rec...
Reflections are very common phenomena in our daily photography, which
di...
Reliable estimation of illuminant chromaticity is crucial for simulating...
In recent years we have witnessed tremendous progress in unpaired
image-...
Analyzing human motion is a challenging task with a wide variety of
appl...
Recent GAN-based architectures have been able to deliver impressive
perf...
We present a new video-based performance cloning technique. After traini...
We present SAGNet, a structure-aware generative model for 3D shapes. Giv...
Unsupervised domain adaptation aims at learning a shared model for two
r...
The real world exhibits an abundance of non-stationary textures. Example...
Correspondence between images is a fundamental problem in computer visio...
Contextual information provides important cues for disambiguating visual...
Object cutout is a fundamental operation for image editing and manipulat...
Human 3D pose estimation from a single image is a challenging task with
...
We present a technique for designing 3D-printed perforated lampshades, w...