• Publications
  • Influence
A Database and Evaluation Methodology for Optical Flow
TLDR
The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. Expand
  • 2,188
  • 314
  • PDF
A Naturalistic Open Source Movie for Optical Flow Evaluation
TLDR
We introduce a new optical flow data set derived from the open source 3D animated short film Sintel. Expand
  • 1,132
  • 240
  • PDF
SMPL: a skinned multi-person linear model
TLDR
We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Expand
  • 880
  • 188
  • PDF
Secrets of optical flow estimation and their principles
TLDR
We derive a new objective that formalizes the median filtering heuristic. Expand
  • 1,308
  • 159
  • PDF
End-to-End Recovery of Human Shape and Pose
TLDR
We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. Expand
  • 603
  • 157
  • PDF
Towards Understanding Action Recognition
Although action recognition in videos is widely studied, current methods often fail on real-world datasets. Many recent approaches improve accuracy and robustness to cope with challenging videoExpand
  • 500
  • 151
  • PDF
The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
TLDR
This paper presents a framework based onrobust estimation that addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions, and provides examples with natural and synthetic image sequences. Expand
  • 1,751
  • 150
  • PDF
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion
TLDR
We present data obtained using a hardware system that is able to capture synchronized video and ground-truth 3D motion. Expand
  • 849
  • 138
  • PDF
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
TLDR
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. Expand
  • 675
  • 131
  • PDF
On Human Motion Prediction Using Recurrent Neural Networks
TLDR
We propose three changes to the standard RNN models typically used for human motion, which results in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction. Expand
  • 328
  • 107
  • PDF
...
1
2
3
4
5
...