• Publications
  • Influence
Unique Signatures of Histograms for Local Surface Description
tl;dr
We propose a novel comprehensive proposal for surface representation, which encompasses a new unique and repeatable local reference frame as well as a new 3D descriptor. Expand
  • 1,030
  • 195
  • Open Access
Deeper Depth Prediction with Fully Convolutional Residual Networks
tl;dr
We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps. Expand
  • 766
  • 162
  • Open Access
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
tl;dr
We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot. Expand
  • 314
  • 83
  • Open Access
SHOT: Unique signatures of histograms for surface and texture description
tl;dr
We first propose a comprehensive proposal which encompasses a repeatable local referenceframe as well as a 3D descriptor, the latter featuring an hybrid structurebetween Signatures and Histograms. Expand
  • 287
  • 46
  • Open Access
Unique shape context for 3d data description
tl;dr
We show how to deploy a unique local Reference Frame to improve the accuracy and reduce the memory footprint of the well-known Shape Context descriptor. Expand
  • 191
  • 41
  • Open Access
CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction
tl;dr
We propose a method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM, based on a scheme that privileges depth prediction in image locations where monocularSLAM approaches tend to fail, e.g. along low-textured regions. Expand
  • 298
  • 34
  • Open Access
A combined texture-shape descriptor for enhanced 3D feature matching
tl;dr
We present a novel descriptor for feature matching in 3D data enriched with texture. Expand
  • 269
  • 32
  • Open Access
Tutorial: Point Cloud Library: Three-Dimensional Object Recognition and 6 DOF Pose Estimation
tl;dr
With the advent of new-generation depth sensors, the use of three-dimensional (3-D) data is becoming increasingly popular. Expand
  • 298
  • 25
  • Open Access
BOP: Benchmark for 6D Object Pose Estimation
tl;dr
We propose a benchmark for 6D object pose estimation that includes eight datasets in a unified format, an evaluation methodology, a comprehensive evaluation of 15 recent methods, and an online evaluation system open for continuous submission of new results. Expand
  • 105
  • 24
  • Open Access
Registration with the Point Cloud Library: A Modular Framework for Aligning in 3-D
tl;dr
This article presents the open-source point cloud library (PCL) and the tools available for point cloud registration. Expand
  • 164
  • 23
  • Open Access