Neural fields, a category of neural networks trained to represent
high-f...
Denoising diffusion models have shown great promise in human motion synt...
We present a novel method for populating 3D indoor scenes with virtual h...
Automatic perception of human behaviors during social interactions is cr...
Recent years have witnessed significant progress in the field of neural
...
We present Factor Fields, a novel framework for modeling and representin...
We present HARP (HAnd Reconstruction and Personalization), a personalize...
Segmenting humans in 3D indoor scenes has become increasingly important ...
Combining human body models with differentiable rendering has recently
e...
Modern 3D semantic instance segmentation approaches predominantly rely o...
Parametric 3D body models like SMPL only represent minimally-clothed peo...
Synthesizing natural interactions between virtual humans and their 3D
en...
While methods that regress 3D human meshes from images have progressed
r...
Image-based volumetric avatars using pixel-aligned features promise
gene...
Temporal alignment of fine-grained human actions in videos is important ...
Deep learning depends on large amounts of labeled training data. Manual
...
We present a novel neural implicit representation for articulated human
...
Humans are in constant contact with the world as they move through it an...
Human grasping synthesis has numerous applications including AR/VR, vide...
Our goal is to populate digital environments, in which the digital human...
Understanding social interactions from first-person views is crucial for...
We present Hand ArticuLated Occupancy (HALO), a novel representation of
...
Currently it requires an artist to create 3D human avatars with realisti...
Recovering high-quality 3D human motion in complex scenes from monocular...
In natural conversation and interaction, our hands often overlap or are ...
In this paper, we aim to create generalizable and controllable neural si...
Registering point clouds of dressed humans to parametric human models is...
Learning to model and reconstruct humans in clothing is challenging due ...
Substantial progress has been made on modeling rigid 3D objects using de...
People touch their face 23 times an hour, they cross their arms and legs...
A key step towards understanding human behavior is the prediction of 3D ...
To understand human daily social interaction from egocentric perspective...
High fidelity digital 3D environments have been proposed in recent years...
In recent years, substantial progress has been made on robotic grasping ...
Gaze estimation is a fundamental task in many applications of computer
v...
The modeling of human motion using machine learning methods has been wid...
We present a fully-automatic system that takes a 3D scene and generates
...
We address the challenging task of anticipating human-object interaction...
The optical flow of humans is well known to be useful for the analysis o...
Neural networks need big annotated datasets for training. However, manua...
Three-dimensional human body models are widely used in the analysis of h...
Three-dimensional human body models are widely used in the analysis of h...
Bilinear pooling is capable of extracting high-order information from da...
We propose a novel end-to-end trainable framework for the graph decompos...
Fine-grained temporal action parsing is important in many applications, ...
We propose a novel network that learns a part-aligned representation for...
We present an effective dynamic clustering algorithm for the task of tem...
Learning how to generate descriptions of images or videos received major...
In this paper we propose an approach for articulated tracking of multipl...
We state a combinatorial optimization problem whose feasible solutions d...