• Publications
  • Influence
Multilinear pose and body shape estimation of dressed subjects from image sets
TLDR
In this paper we propose a multilinear model of human pose and body shape which is estimated from a database of registered 3D body scans in different poses. Expand
  • 116
  • 10
  • PDF
Clustering with Hypergraphs: The Case for Large Hyperedges
TLDR
We show that large hyperedges are better from both a theoretical and an empirical standpoint than the smallest possible hyperedge size, due to a lack of study into the potential benefits and effective algorithms to generate them. Expand
  • 54
  • 6
  • PDF
Uncalibrated Factorization Using a Variable Symmetric Affine Camera
TLDR
In order to reconstruct 3-D Euclidean shape by the Tomasi-Kanade factorization, one needs to specify an affine camera model such as orthographic, weak perspective, and paraperspective. Expand
  • 19
  • 4
  • PDF
On Support Relations and Semantic Scene Graphs
TLDR
This paper proposes a novel framework for automatic generation of semantic scene graphs describing the contextual relations within a cluttered indoor scene which interpret indoor environments. Expand
  • 35
  • 2
  • PDF
3D Reconstruction of Human Motion from Monocular Image Sequences
TLDR
This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Expand
  • 41
  • 1
  • PDF
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
TLDR
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. Expand
  • 9
  • 1
  • PDF
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection
TLDR
We present a novel approach for vanishing point detection from uncalibrated monocular images. Expand
  • 22
  • PDF
A Kinematic Chain Space for Monocular Motion Capture
TLDR
We present a method based on projecting an observation into a kinematic chain space (KCS). Expand
  • 16
  • PDF
3D human motion capture from monocular image sequences
TLDR
This paper tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Expand
  • 9
  • PDF
Apathy Is the Root of All Expressions
TLDR
In this paper, we present a new statistical model for human faces. Expand
  • 8
  • PDF
...
1
2
3
4
5
...