DeepIM: Deep Iterative Matching for 6D Pose Estimation

@article{Li2018DeepIMDI,
  title={DeepIM: Deep Iterative Matching for 6D Pose Estimation},
  author={Yi Li and Gu Wang and Xiangyang Ji and Yu Xiang and Dieter Fox},
  journal={International Journal of Computer Vision},
  year={2018},
  volume={128},
  pages={657-678}
}
  • Yi LiGu Wang D. Fox
  • Published 31 March 2018
  • Computer Science
  • International Journal of Computer Vision
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. [] Key Method Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks…
View on Springer
arxiv.org
442 Citations
Highly Influential Citations
71
Background Citations
186
Methods Citations
221
Results Citations
19

442 Citations

DeepRM: Deep Recurrent Matching for 6D Pose Refinement

The proposed DeepRM is a novel recurrent network architecture for 6D pose estimation that is trained end-to-end, and uses a scalable backbone that can be tuned via a single parameter for accuracy and efficiency.

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation

This work proposes to integrate deep neural networks with 3D generative representations of objects into a unified neural architecture that is termed NeMo, which learns a generative model of neural feature activations at each vertex on a dense 3D mesh.

Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects

This work proposes a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose, and demonstrates that this method boosts performances for supervised category pose estimation on standard benchmarks.

RMTrack: 6D Object Pose Tracking by Continuous Image Render Match

This work proposes a deep learning architecture for 6D object pose estimation, and a neural network that can predict object movement, and introduces an efficient way of representing object motion, which can reduce the influence of the field of view and object scale.

DRNet: A Depth-Based Regression Network for 6D Object Pose Estimation

This paper introduces a translation estimation module to provide an initial translation based on an estimated depth map, and designs a new loss function function for symmetric objects, an approach that has handled such exceptionally difficult cases in prior works.

Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction

This work proposes a learning framework in which a Graph Convolutional Neural Network reconstructs a Pose Conditioned 3D mesh of the object, and is capable of self validating its pose estimation by measuring the quality of the reconstructed mesh, which is invaluable in real life applications.

DPOD: 6D Pose Object Detector and Refiner

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.

L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation With Small Datasets

This letter proposes a novel approach to perform 6 DoF object pose estimation from a single RGB-D image in two stages: data-driven and geometric respectively, which is more robust and accurate than state-of-the-art methods.

Trace-Level Invisible Enhanced Network for 6D Pose Estimation

This paper intro-duces INVNet, integrating invisible information into the visi-ble 2D-3D correspondence to model geometry features of the 3D object, and proposes Trace-level Geometry Path, which estimates the trace-level depth of the object model for each image pixel.

Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images

This paper proposes a method, Neural Object Learning (NOL), that creates synthetic images of objects in arbitrary poses by combining only a few observations from cluttered images, and a novel refinement step is proposed to align inaccurate poses in source images, which results in better quality images.
...

References

SHOWING 1-10 OF 68 REFERENCES

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.

Deep Model-Based 6D Pose Refinement in RGB

A new visual loss is proposed that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model and producing pose accuracies that come close to 3D ICP without the need for depth data.

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.

Geometric Loss Functions for Camera Pose Regression with Deep Learning

  • Alex KendallR. Cipolla
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
A number of novel loss functions for learning camera pose which are based on geometry and scene reprojection error are explored, and it is shown how to automatically learn an optimal weighting to simultaneously regress position and orientation.

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.

Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images

This work describes the posterior density of a particular object pose with a convolutional neural network (CNN) that compares observed and rendered images and observes empirically that the CNN does not specialize to the geometry or appearance of specific objects.

BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth

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.

Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image

A regularized, auto-context regression framework is developed which iteratively reduces uncertainty in object coordinate and object label predictions and an efficient way to marginalize object coordinate distributions over depth is introduced to deal with missing depth information.

Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects

This network is the first deep network trained only on synthetic data that is able to achieve state-of-the-art performance on 6-DoF object pose estimation and demonstrates a real-time system estimating object poses with sufficient accuracy for real-world semantic grasping of known household objects in clutter by a real robot.

PoseRBPF: A Rao–Blackwellized Particle Filter for 6-D Object Pose Tracking

This work forms 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, and achieves state-of-the-art results on two 6D pose estimation benchmarks.
...