Corpus ID: 209500788

W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression

  title={W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression},
  author={Zelin Xu and Ke Chen and Kui Jia},
  • Zelin Xu, Ke Chen, K. Jia
  • Published 26 December 2019
  • Computer Science
  • ArXiv
Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired data under an uncontrolled environment. This paper introduces a novel pose estimation algorithm W-PoseNet, which densely regresses from input data to 6D pose and also 3D coordinates in model space. In other words, local features learned for pose regression… Expand
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
A deep neural network is trained to regress 6D object pose based on geometrically stable patch groups via learning both intra-patch geometric features and inter-patch contextual features, and achieves the state-of-the-art results on public benchmarks. Expand
6D Object Pose Estimation With Color/Geometry Attention Fusion
  • Honglin Yuan, R. Veltkamp
  • Computer Science
  • 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)
  • 2020
This work proposes a novel approach that effectively extracts color and depth features from RGB-D images considering the local and global geometric relationships and applies a graph attention mechanism to fully exploit representations between these features and fuse them together to predict the 6D pose of a given object. Expand
PAM: Point-wise Attention Module for 6D Object Pose Estimation
A Point Attention Module that can efficiently extract powerful feature from RGB-D is proposed that outperforms the existing methods in benchmarks, YCB Video and LineMod and shows that the performance significantly improved compared to the existing model. Expand
Survey on 6D Pose Estimation of Rigid Object
It is found that deep learning combined with traditional methods can produce better results in object pose estimation, and pose ambiguity which is an open problem needed further study. Expand
DualPoseNet: Category-level 6D Object Pose and Size Estimation using Dual Pose Network with Refined Learning of Pose Consistency
It is the novel introduction of the implicit decoder that enables the refined pose prediction during testing, by enforcing the predicted pose consistency between the two decoders using a self-adaptive loss term. Expand
From IR Images to Point Clouds to Pose: Point Cloud-Based AR Glasses Pose Estimation
Two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation are proposed, one based on a Deep Neural Network alone and the other a hybrid model combining Deep Learning and a voting-based mechanism. Expand
3D Object Classification on Partial Point Clouds: A Practical Perspective
A novel algorithm in an alignment-classification manner is proposed in this paper, which consists of an alignment module predicting object pose for the rigid transformation of visible point clouds to their canonical pose and a typical point classifier such as PointNet++ and DGCNN. Expand


Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd
This work proposes an unsupervised feature learnt from depth-invariant patches using a Sparse Autoencoder and offers an extensive evaluation of various state of the art features, and learns to estimate the reduction of uncertainty in other views, formulating the problem of selecting the next-best-view. Expand
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
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
Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation
A novel method for robust and accurate 3D object pose estimation from a single color image under large occlusions by predicting heatmaps from multiple small patches independently and then computing the 3D pose from these correspondences using a geometric method. Expand
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
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
6-DoF object pose from semantic keypoints
A novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image by combining semantic keypoints predicted by a convolutional network with a deformable shape model. 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
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
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation
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
Viewpoints and keypoints
The problem of pose estimation for rigid objects in terms of determining viewpoint to explain coarse pose and keypoint prediction to capture the finer details is characterized and it is demonstrated that leveraging viewpoint estimates can substantially improve local appearance based keypoint predictions. Expand
Learning 6D Object Pose Estimation Using 3D Object Coordinates
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
Global Hypothesis Generation for 6D Object Pose Estimation
This paper addresses the task of estimating the 6D-pose of a known 3D object from a single RGB-D image with a novel fully-connected Conditional Random Field that outputs a very small number of pose-hypotheses and gives a new, efficient two-step optimization procedure. Expand