J
Javier Romero
Researcher at Max Planck Society
Publications - 69
Citations - 13423
Javier Romero is an academic researcher from Max Planck Society. The author has contributed to research in topics: Pose & Optical flow. The author has an hindex of 34, co-authored 68 publications receiving 9209 citations. Previous affiliations of Javier Romero include Amazon.com & Royal Institute of Technology.
Papers
More filters
Journal ArticleDOI
SMPL: a skinned multi-person linear model
TL;DR: The Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses that is compatible with existing graphics pipelines and iscompatible with existing rendering engines.
Book ChapterDOI
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
Federica Bogo,Angjoo Kanazawa,Christoph Lassner,Christoph Lassner,Peter V. Gehler,Peter V. Gehler,Javier Romero,Michael J. Black +7 more
TL;DR: In this article, the authors estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image by fitting a statistical body shape model to the 2D joints.
Proceedings ArticleDOI
A Simple Yet Effective Baseline for 3d Human Pose Estimation
TL;DR: In this paper, a relatively simple deep feed-forward network was proposed to estimate 3D human pose from 2D joint locations with a remarkably low error rate, achieving state-of-the-art results on Human3.6M.
Proceedings ArticleDOI
Learning from Synthetic Humans
Gül Varol,Javier Romero,Xavier Martin,Naureen Mahmood,Michael J. Black,Ivan Laptev,Cordelia Schmid +6 more
TL;DR: SURREAL as mentioned in this paper ) is a large-scale dataset with synthetically generated but realistic images of people rendered from 3D sequences of human motion capture data, which allows for accurate human depth estimation and human part segmentation in real RGB images.
Proceedings ArticleDOI
On Human Motion Prediction Using Recurrent Neural Networks
TL;DR: It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction.