Learning 6D Object Pose Estimation Using 3D Object Coordinates

@inproceedings{Brachmann2014Learning6O,
  title={Learning 6D Object Pose Estimation Using 3D Object Coordinates},
  author={Eric Brachmann and Alexander Krull and Frank Michel and Stefan Gumhold and Jamie Shotton and Carsten Rother},
  booktitle={ECCV},
  year={2014}
}
This work addresses the problem of estimating the 6D Pose of specific objects from a single RGB-D image. [...] Key Method We are able to show that for a common dataset with texture-less objects, where template-based techniques are suitable and state of the art, our approach is slightly superior in terms of accuracy. We also demonstrate the benefits of our approach, compared to template-based techniques, in terms of robustness with respect to varying lighting conditions. Towards this end, we contribute a new…Expand

Figures, Tables, and Topics from this paper

BOP: Benchmark for 6D Object Pose Estimation
TLDR
A benchmark for 6D pose estimation of a rigid object from a single RGB-D input image shows that methods based on point-pair features currently perform best, outperforming template matching methods, learning-based methods and methodsbased on 3D local features. Expand
DPOD: Dense 6D Pose Object Detector in RGB images
TLDR
This work proposes a new method for simultaneous object detection and 6DoF pose estimation that is real-time capable, conceptually simple and not bound to any particular detection paradigms, such as R-CNN, SSD or YOLO. Expand
Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
TLDR
This paper solves the key problem of existing methods requiring expensive 3D pose annotations by proposing a new method that matches RGB images to CAD models for object pose estimation and can reliably estimate object pose in RGB images and generalize to object instances not seen during training. Expand
6-DoF object pose from semantic keypoints
TLDR
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
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image
TLDR
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. Expand
PointPoseNet: Point Pose Network for Robust 6D Object Pose Estimation
TLDR
A novel pipeline to estimate 6D object pose from RGB-D images of known objects present in complex scenes by taking the point cloud as input and regresses the point-wise unit vectors pointing to the 3D keypoints to generate keypoint hypotheses from which the 6Dobject pose hypotheses are computed. Expand
EPOS: Estimating 6D Pose of Objects With Symmetries
TLDR
A new method for estimating the 6D pose of rigid objects with available 3D models from a single RGB input image using a robust and efficient variant of the PnP-RANSAC algorithm, which outperforms all RGB and most RGB-D and D methods on the T-LESS and LM-O datasets. Expand
SilhoNet: An RGB Method for 6D Object Pose Estimation
TLDR
A novel method called SilhoNet is introduced that predicts 6D object pose from monocular images using a convolutional neural network pipeline that takes in region of interest proposals to simultaneously predict an intermediate silhouette representation for objects with an associated occlusion mask and a 3D translation vector. Expand
Segmentation-Driven 6D Object Pose Estimation
TLDR
This paper introduces a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations and uses a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences. Expand
Learning latent geometric consistency for 6D object pose estimation in heavily cluttered scenes
TLDR
A dual-stream network for estimating 6D pose of a set of known objects from RGB-D images is presented and it is shown that this method outperforms state-of-the-art approaches on 6D object pose estimation in two challenging datasets, YCB-Video and LineMOD. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes
TLDR
A framework for automatic modeling, detection, and tracking of 3D objects with a Kinect and shows how to build the templates automatically from 3D models, and how to estimate the 6 degrees-of-freedom pose accurately and in real-time. Expand
3D LayoutCRF for Multi-View Object Class Recognition and Segmentation
TLDR
An approach to accurately detect and segment partially occluded objects in various viewpoints and scales is introduced and a novel framework for combining object-level descriptions with pixel-level appearance, boundary, and occlusion reasoning is introduced. Expand
Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach
TLDR
This paper starts from the template-based approach based on the LINE2D/LINEMOD representation, yet extends it in two ways to learn the templates in a discriminative fashion, and proposes a scheme based on cascades that speeds up detection. Expand
Real-time human pose recognition in parts from single depth images
TLDR
This work takes an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem, and generates confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes. Expand
Efficient Human Pose Estimation from Single Depth Images
TLDR
Two new approaches to human pose estimation are described, both of which can quickly and accurately predict the 3D positions of body joints from a single depth image without using any temporal information. Expand
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. Our approach employs a regression forest that is capable of inferringExpand
Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery
TLDR
This paper demonstrates that the proposed DEHV scheme can be successfully employed as a key building block in two application scenarios (highly accurate 6 degrees of freedom (6 DOF) pose estimation and 3D object modeling). Expand
Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach
TLDR
The method is geared for fast and scalable learning and detection by combining tr actable extraction of edgelet constellations with library lookup based on rotation and s cale-invariant descriptors. Expand
Model globally, match locally: Efficient and robust 3D object recognition
TLDR
A novel method is proposed that creates a global model description based on oriented point pair features and matches that model locally using a fast voting scheme, which allows using much sparser object and scene point clouds, resulting in very fast performance. Expand
Keypoint recognition using randomized trees
  • V. Lepetit, P. Fua
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
TLDR
A keypoint-based approach is developed that is effective in this context by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem, which shifts much of the computational burden to a training phase, without sacrificing recognition performance. Expand
...
1
2
3
4
...