• Publications
  • Influence
3D Bounding Box Estimation Using Deep Learning and Geometry
TLDR
We present a method for 3D object detection and pose estimation from a single image. Expand
  • 375
  • 61
  • PDF
Synthesizing Training Data for Object Detection in Indoor Scenes
TLDR
We explore the ability of using synthetically generated composite images for training state-of-the-art object detectors, especially for object instance detection. Expand
  • 89
  • 14
  • PDF
Multiview RGB-D Dataset for Object Instance Detection
TLDR
This paper presents a new multi-view RGB-D dataset of nine kitchen scenes, each containing several objects in realistic cluttered environments including a subset of objects from the BigBird dataset. Expand
  • 36
  • 8
  • PDF
Visual Representations for Semantic Target Driven Navigation
TLDR
We propose to use semantic segmentation and detection masks as observations obtained by state-of-the-art computer vision algorithms and use a deep network to learn the navigation policy. Expand
  • 64
  • 7
  • PDF
Deep Convolutional Features for Image Based Retrieval and Scene Categorization
TLDR
We propose a simple, yet effective, image representation derived from CNNs pre-trained on ImageNet and Places datasets. Expand
  • 30
  • 5
  • PDF
6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
TLDR
We introduce the first learning-based framework for efficiently generating diverse sets of stable grasps for unknown objects. Expand
  • 58
  • 4
  • PDF
PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking
TLDR
We formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the3D translation of an object are decoupled. Expand
  • 25
  • 2
  • PDF
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
TLDR
Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation from a single RGB image. Expand
  • 29
  • 2
Semantically guided location recognition for outdoors scenes
TLDR
The problem of image based localization has a long history both in robotics and computer vision and shares many similarities with image based retrieval problem. Expand
  • 19
  • 1
  • PDF
A comparative study of control architectures in UAV/UGV-based surveillance system
TLDR
The goal of this paper is to study the characteristics of various control architectures (e.g. centralized, hierarchical, distributed, and hybrid) for a team of unmanned aerial vehicles (UAVs) and UGVs) in performing collaborative surveillance and crowd control. Expand
  • 10
  • 1
  • PDF