We present a novel approach to the generation of static and articulated ...
We introduce Text2Cinemagraph, a fully automated method for creating
cin...
Text-to-image diffusion models can create stunning images from natural
l...
Game engines are powerful tools in computer graphics. Their power comes ...
Existing 3D-from-2D generators are typically designed for well-curated
s...
Building animatable and editable models of clothed humans from raw 3D sc...
We propose a novel approach for unsupervised 3D animation of non-rigid
d...
Modern 3D-GANs synthesize geometry and texture by training on large-scal...
Existing 3D-aware image synthesis approaches mainly focus on generating ...
With the success of Vision Transformers (ViTs) in computer vision tasks,...
Recent efforts in Neural Rendering Fields (NeRF) have shown impressive
r...
Natural language interaction is a promising direction for democratizing ...
In this work, we present a novel framework built to simplify 3D asset
ge...
There has been a recent explosion of impressive generative models that c...
In this work, we explore the emotional reactions that real-world images ...
Recently, sparse training has emerged as a promising paradigm for effici...
Creating and editing the shape and color of 3D objects require tremendou...
A very recent trend in generative modeling is building 3D-aware generato...
Diffusion probabilistic models (DPMs) have become a popular approach to
...
Vision Transformers (ViT) have shown rapid progress in computer vision t...
We present a novel method for performing flexible, 3D-aware image conten...
We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal
fr...
Recent research explosion on Neural Radiance Field (NeRF) shows the
enco...
Most methods for conditional video synthesis use a single modality as th...
We present Playable Environments - a new representation for interactive ...
Neural network quantization is a promising compression technique to redu...
We present a novel method to acquire object representations from online ...
Videos show continuous events, yet most - if not all - video synthesis
f...
Human motion retargeting aims to transfer the motion of one person in a
...
Image and video synthesis are closely related areas aiming at generating...
We propose novel motion representations for animating articulated object...
A common assumption in multimodal learning is the completeness of traini...
Generative Adversarial Networks (GANs) have achieved huge success in
gen...
This paper introduces the unsupervised learning problem of playable vide...
Despite the recent success of face image generation with GANs, condition...
In this paper, we present a learning-based method to the keyframe-based ...
In this paper, we propose a generic neural-based hair rendering pipeline...
Recent co-part segmentation methods mostly operate in a supervised learn...
In this paper, we tackle the problem of human motion transfer, where we
...
Image animation consists of generating a video sequence so that an objec...
We introduce a novel domain adaptation formulation from synthetic datase...
We propose a novel approach to performing fine-grained 3D manipulation o...
Tracking user reported bugs requires considerable engineering effort in ...
We present a method for fine-grained face manipulation. Given a face ima...
Deep neural network models trained on large labeled datasets are the
sta...
Visual signals in a video can be divided into content and motion. While
...