• Publications
  • Influence
Global contrast based salient region detection
TLDR
We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. Expand
  • 3,021
  • 467
  • PDF
Super 4PCS Fast Global Pointcloud Registration via Smart Indexing
TLDR
We present SUPER 4PCS, a fast global registration for pointsets, which runs in optimal linear time and is output sensitive in the complexity of the alignment problem based on the (unknown) overlap across scan pairs. Expand
  • 256
  • 35
  • PDF
Robust global registration
TLDR
We present an algorithm for the automatic alignment of two 3D shapes (data and model), without any assumptions about their initial positions. Expand
  • 603
  • 29
  • PDF
Partial and approximate symmetry detection for 3D geometry
TLDR
This paper presents a new algorithm that processes geometric models and efficiently discovers and extracts a compact representation of their Euclidean symmetries. Expand
  • 454
  • 26
  • PDF
SalientShape: group saliency in image collections
TLDR
We propose a simple, fast, and effective algorithm for locating and segmenting salient objects in large image collections by analysing image collections. Expand
  • 219
  • 26
  • PDF
Geometric modeling in shape space
TLDR
We present a novel framework to treat shapes in the setting of Riemannian geometry as points in a shape space to aid the user in design and modeling tasks, especially to explore the space of deformations of a given shape. Expand
  • 273
  • 19
PCPNet Learning Local Shape Properties from Raw Point Clouds
TLDR
In this paper, we propose PCPNET, a deep‐learning based approach for estimating local 3D shape properties in point clouds. Expand
  • 112
  • 16
  • PDF
Discovering structural regularity in 3D geometry
TLDR
We introduce a computational framework for discovering regular or repeated geometric structures in 3D shapes. Expand
  • 211
  • 15
Registration of point cloud data from a geometric optimization perspective
TLDR
We propose a framework for pairwise registration of shapes represented by point cloud data (PCD). Expand
  • 276
  • 15
  • PDF
Estimating surface normals in noisy point cloud data
TLDR
In this paper we describe and analyze a method based on local least square fitting for estimating the normals at all sample points of a point cloud data (PCD) set, in the presence of noise. Expand
  • 334
  • 13