HybridPose: 6D Object Pose Estimation Under Hybrid Representations

@article{Song2020HybridPose6O,
  title={HybridPose: 6D Object Pose Estimation Under Hybrid Representations},
  author={Chen Song and Jiaru Song and Qi-Xing Huang},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={428-437}
}
We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). Different intermediate… Expand
KDFNet: Learning Keypoint Distance Field for 6D Object Pose Estimation
TLDR
KDFNet is presented, a novel method for 6D object pose estimation from RGB images able to robustly estimate the 6D pose in challenging scenarios including occlusion and achieves state-ofthe-art performance on Occlusion LINEMOD dataset. Expand
Automatic 3D Object Recognition and Localization for Robotic Grasping
TLDR
The primary purpose of this paper is to join Machine Learning models for detection and pose estimation into an automatic system to be used in a grasping environment, and shows promising results for simpler objects, even with training on a reduced dataset. Expand
Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview
TLDR
This paper presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route, and compares results of current state-of-the-art methods on several publicly available datasets. Expand
RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
TLDR
RePOSE leverages image rendering for fast feature extraction using a 3D model with a learnable texture and utilizes differentiable Levenberg-Marquardt (LM) optimization to refine a pose fast and accurately by minimizing the distance between the input and rendered image representations without the need of zooming in. Expand
RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation
TLDR
The method, RePOSE, is a Real-time Iterative Rendering and Refinement algorithm for 6D POSE estimation that achieves state-of-the-art accuracy and can render an image representation in under 1ms. Expand
EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
TLDR
EfficientPose is a new approach for 6D object pose estimation that achieves a new state-of-the-art accuracy of 97.35% in terms of the ADD(-S) metric on the widely-used 6D pose estimation benchmark dataset Linemod using RGB input, while still running end-to-end at over 27 FPS. Expand
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review
TLDR
Three key tasks during vision-based robotic grasping are concluded, which are object localization, object pose estimation and grasp estimation, which include 2D planar grasp methods and 6DoF grasp methods. Expand
3D-FUTURE: 3D Furniture shape with TextURE
TLDR
3D Furniture shape with TextURE (3D-FUTURE) is presented: a richly-annotated and large-scale repository of 3D furniture shapes in the household scenario and baseline experiments are provided on several widely studied tasks, such as joint 2D instance segmentation and 3D object pose estimation. Expand
6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning
  • Lu Zou, Zhangjin Huang
  • Computer Science
  • 2021
TLDR
6D-ViT, a transformer-based instance representation learning network, which is suitable for highly accurate category-level object pose estimation on RGB-D images, achieves state-of-the-art performance on both datasets, and significantly outperforms all existing methods. Expand
A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection
TLDR
This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection, and presents the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 48 REFERENCES
DPOD: 6D Pose Object Detector and Refiner
TLDR
A novel deep learning method that estimates dense multi-class 2D-3D correspondence maps between an input image and available 3D models and demonstrates that a large number of correspondences is beneficial for obtaining high-quality 6D poses both before and after refinement. Expand
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation
TLDR
A Pixel-wise Voting Network (PVNet) is introduced to regress pixel-wise vectors pointing to the keypoints and use these vectors to vote for keypoint locations, which creates a flexible representation for localizing occluded or truncated keypoints. Expand
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
EPnP: An Accurate O(n) Solution to the PnP Problem
TLDR
A non-iterative solution to the PnP problem—the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences—whose computational complexity grows linearly with n, which can be done in O(n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12×12 matrix. Expand
Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation
TLDR
A novel pose estimation method that predicts the 3D coordinates of each object pixel without textured models, and a novel loss function, the transformer loss, is proposed to handle symmetric objects by guiding predictions to the closest symmetric pose. Expand
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
TLDR
This work introduces PoseCNN, a new Convolutional Neural Network for 6D object pose estimation, which is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input. Expand
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
  • Mahdi Rad, V. Lepetit
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
TLDR
A novel method for 3D object detection and pose estimation from color images only that uses segmentation to detect the objects of interest in 2D even in presence of partial occlusions and cluttered background and is the first to report results on the Occlusion dataset using color imagesonly. Expand
Learning 6D Object Pose Estimation Using 3D Object Coordinates
TLDR
This work addresses the problem of estimating the 6D Pose of specific objects from a single RGB-D image by presenting a learned, intermediate representation in form of a dense 3D object coordinate labelling paired with a dense class labelling. Expand
CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation
TLDR
This work proposes a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation. Expand
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
TLDR
DenseFusion is a generic framework for estimating 6D pose of a set of known objects from RGB-D images that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Expand
...
1
2
3
4
5
...