Existing methods for the 4D reconstruction of general, non-rigidly defor...
Recent methods for 3D reconstruction and rendering increasingly benefit ...
Creating realistic virtual assets is a time-consuming process: it usuall...
Neural Radiance Fields (NeRFs) encode the radiance in a scene parameteri...
The capture and animation of human hair are two of the major challenges ...
Coordinate-based volumetric representations have the potential to genera...
Learning geometry, motion, and appearance priors of object classes is
im...
We present Virtual Elastic Objects (VEOs): virtual objects that not only...
Novel view synthesis for humans in motion is a challenging computer visi...
Capturing and rendering life-like hair is particularly challenging due t...
We propose a novel approach for 3D video synthesis that is able to repre...
The combination of traditional rendering with neural networks in Deferre...
We present Non-Rigid Neural Radiance Fields (NR-NeRF), a reconstruction ...
We present TexMesh, a novel approach to reconstruct detailed human meshe...
Differentiable rendering in combination with deep learning promises grea...
In this paper, we propose ARCH (Animatable Reconstruction of Clothed Hum...
The goal of many computer vision systems is to transform image pixels in...
With the increased availability of 3D scanning technology, point clouds ...
Direct prediction of 3D body pose and shape remains a challenge even for...
We present the first image-based generative model of people in clothing ...
Early stopping is a widely used technique to prevent poor generalization...
3D models provide a common ground for different representations of human...
We describe the first method to automatically estimate the 3D pose of th...