• Home
  • Search
  • 3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings
  • Open Access IconOpen Access
  • Cite Icon27
  • https://doi.org/10.1007/978-3-030-69525-5_3Copy DOI Icon

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

  • Jan 1, 2021
  • Giorgia Pitteri +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We present an approach for detecting and estimating the 3D poses of objects\nin images that requires only an untextured CAD model and no training phase for\nnew objects. Our approach combines Deep Learning and 3D geometry: It relies on\nan embedding of local 3D geometry to match the CAD models to the input images.\nFor points at the surface of objects, this embedding can be computed directly\nfrom the CAD model; for image locations, we learn to predict it from the image\nitself. This establishes correspondences between 3D points on the CAD model and\n2D locations of the input images. However, many of these correspondences are\nambiguous as many points may have similar local geometries. We show that we can\nuse Mask-RCNN in a class-agnostic way to detect the new objects without\nretraining and thus drastically limit the number of possible correspondences.\nWe can then robustly estimate a 3D pose from these discriminative\ncorrespondences using a RANSAC- like algorithm. We demonstrate the performance\nof this approach on the T-LESS dataset, by using a small number of objects to\nlearn the embedding and testing it on the other objects. Our experiments show\nthat our method is on par or better than previous methods.\n

Similar Papers
  • Research Article
  • Citations1

МОДЕЛЬ И МЕТОД ДЛЯ ОБНАРУЖЕНИЯ ЦВЕТНЫХ ОБЪЕКТОВ С ИСПОЛЬЗОВАНИЕМ МОДИФИЦИРОВАННОГО ПРЕОБРАЗОВАНИЯ РАДИАЛЬНОЙ СИММЕТРИИ

  • Jan 01, 2021
  • Vestnik of Ryazan State Radio Engineering University
  • R M Shakirzyanov +1
  • Book Chapter
  • Citations7

Scene Perception and Recognition in Industrial Environments for Human-Robot Interaction

  • Jan 01, 2013
  • Nikhil Somani +3
  • Research Article
  • Citations30

An MRF model-based approach to the detection of rectangular shape objects in color images

  • May 10, 2007
  • Signal Processing
  • Yangxing Liu +2
  • Conference Article

Estimation of 3D Information of multiple objects in a monocular Image

  • Mar 13, 2021
  • Takuma Hirose +2
  • Conference Article
  • Citations4

Bayesian supervised segmentation of objects in natural images using low-level information

  • Sep 18, 2003
  • J Boldys
  • Conference Article
  • Citations52

3D object detection and pose estimation from depth image for robotic bin picking

  • Aug 01, 2014
  • Hao-Yuan Kuo +3
  • Conference Article
  • Citations2

Dependable 3D object recognition with two-layered particle filter

  • Feb 21, 2011
  • Sukhan Lee +1
  • Conference Article
  • Citations3

Controlling illumination color to enhance object discriminability

  • Jun 15, 1992
  • M Vriesenga +3
  • Conference Article
  • Citations50

Floating point HOG implementation for real-time multiple object detection

  • Aug 01, 2012
  • Mateusz Komorkiewicz +2
  • Conference Article
  • Citations250

Single image 3D object detection and pose estimation for grasping

  • May 01, 2014
  • Menglong Zhu +7
  • PDF
  • Research Article
  • Citations59

An Image-Based Hierarchical Deep Learning Framework for Coal and Gangue Detection

  • Jan 01, 2019
  • IEEE Access
  • Dongjun Li +6
  • Conference Article
  • Citations86

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

  • Jun 01, 2022
  • Van Nguyen Nguyen +4
  • Book Chapter
  • Citations8

Semi-Automatic Detection and Extraction of Man-Made Objects in Multispectral Aerial and Satellite Images

  • Jan 01, 1995
  • Vittala K. Shettigara +2
  • Book Chapter

An Object Detection and Pose Estimation Method for AR Application

  • Jan 01, 2022
  • Tengteng Ji +2
  • Research Article
  • Citations20

3D Object Detection and Recognition for Robotic Grasping Based on RGB-D Images and Global Features

  • Sep 01, 2017
  • Foundations of Computing and Decision Sciences
  • Witold Czajewski +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.