• Publications
  • Influence
DensePose: Dense Human Pose Estimation in the Wild
TLDR
This work establishes dense correspondences between an RGB image and a surface-based representation of the human body, a task referred to as dense human pose estimation, and improves accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Expand
Dense Pose Transfer
TLDR
This work proposes a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i.e. synthesize a new image of a person based on a single image of that person and theimage of a pose donor. Expand
Non-rigid 3D Shape Retrieval
TLDR
Evaluation results and comparison analyses described in this paper not only show the bright future in researches of non-rigid 3D shape retrieval but also point out several promising research directions in this topic. Expand
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a directExpand
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
TLDR
A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face images into shading and albedo, and further manipulate face images. Expand
HoloPose: Holistic 3D Human Reconstruction In-The-Wild
TLDR
A part-based model for 3D model parameter regression that allows the HoloPose method to operate in-the-wild, gracefully handling severe occlusions and large pose variation is introduced and validated on challenging benchmarks. Expand
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
TLDR
The proposed system, called DenseReg, allows us to estimate dense image-to-template correspondences in a fully convolutional manner and can provide useful correspondence information as a stand-alone system, while when used as an initialization for Statistical Deformable Models the authors obtain landmark localization results that largely outperform the current state-of-the-art on the challenging 300W benchmark. Expand
Single Image 3D Hand Reconstruction with Mesh Convolutions
TLDR
This paper demonstrates an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes, and shows that the system reconstructs plausible meshes and operates in real-time. Expand
Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues
TLDR
It is demonstrated that if annotations are collected in video frames, their efficacy can be multiplied for free by using motion cues, and that motion cues help much more when they are extracted from videos. Expand
Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model Using Deep Non-Rigid Structure From Motion
TLDR
This work introduces Lifting Autoencoders, a generative 3D surface-based model of object categories that can be controlled in terms of interpretable geometry and appearance factors, allowing it to perform photorealistic image manipulation of identity, expression, 3D pose, and illumination properties. Expand
...
1
2
...