CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation

Li, Zhigang; Gu, Wen; Ji, Xiangyang

doi:10.1109/iccv.2019.00777

Cited by 393 publications

(310 citation statements)

References 17 publications

Supporting

Mentioning

310

Contrasting

Order By: Relevance

“…Methods establishing the correspondences in the opposite direction, i.e. by predicting the 3D object coordinates [4] for a densely sampled set of pixels, have been also proposed [32,46,69,48,39]. As discussed below, none of the existing correspondence-based methods can reliably handle pose ambiguity due to object symmetries.…”

Section: Related Workmentioning

confidence: 99%

EPOS: Estimating 6D Pose of Objects With Symmetries

Hodaň

Baráth

Matas

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

199

140

View full text Add to dashboard Cite

We present a new method for estimating the 6D pose of rigid objects with available 3D models from a single RGB input image. The method is applicable to a broad range of objects, including challenging ones with global or partial symmetries. An object is represented by compact surface fragments which allow handling symmetries in a systematic manner. Correspondences between densely sampled pixels and the fragments are predicted using an encoder-decoder network. At each pixel, the network predicts: (i) the probability of each object's presence, (ii) the probability of the fragments given the object's presence, and (iii) the precise 3D location on each fragment. A data-dependent number of corresponding 3D locations is selected per pixel, and poses of possibly multiple object instances are estimated using a robust and efficient variant of the PnP-RANSAC algorithm. In the BOP Challenge 2019, the method outperforms all RGB and most RGB-D and D methods on the T-LESS and LM-O datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

EPOS: Estimating 6D Pose of Objects With Symmetries

Hodaň

Baráth

Matas

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

199

140

View full text Add to dashboard Cite

show abstract

“…CDPN (Li et al, 2019) uses a detector as a first stage to detect the object in the image. On the second stage the proposed Coordinates-based Disentangled Pose Network splits the computation into two paths: The first regresses the object translation, the second regresses 3D coordinates for all object pixels and uses PnP to compute the object rotation.…”

Section: Related Workmentioning

confidence: 99%

Toward Augmented Reality in Museums: Evaluation of Design Choices for 3D Object Pose Estimation

Panteleris

Michel

Argyros

2021

Front. Virtual Real.

View full text Add to dashboard Cite

The solutions to many computer vision problems, including that of 6D object pose estimation, are dominated nowadays by the explosion of the learning-based paradigm. In this paper, we investigate 6D object pose estimation in a practical, real-word setting in which a mobile device (smartphone/tablet) needs to be localized in front of a museum exhibit, in support of an augmented-reality application scenario. In view of the constraints and the priorities set by this particular setting, we consider an appropriately tailored classical as well as a learning-based method. Moreover, we develop a hybrid method that consists of both classical and learning based components. All three methods are evaluated quantitatively on a standard, benchmark dataset, but also on a new dataset that is specific to the museum guidance scenario of interest.

show abstract

“…Given a known grasp configuration for an object in its local coordinate system, the task of grasping is simplified to estimating the pose of the object such that the grasp pose is transformed into the new scene. Traditional methods identify hand-crafted features to localize an object model within a scene (Klank et al, 2009 ; Srinivasa et al, 2010 ; Chitta et al, 2012a ) but more recently advances for pose estimation have been made by the application of deep learning (Xiang et al, 2018 ; Li et al, 2019 ; Park et al, 2019b ; Zakharov et al, 2019 ) and grasping pipelines achieve high success rate (Tremblay et al, 2018 ; Wang C. et al, 2019 ). The main limitation of this direction of research, however, is the closed-world assumption.…”

Section: Related Workmentioning

confidence: 99%

“…In order to make this extension, we employ the normalized object coordinate space that has been used to estimate the 6D pose of instances (Li et al, 2019 ; Park et al, 2019b ) and classes (Wang H. et al, 2019 ). Since NOC values represent coordinate values in the object's local frame and correspondences between the object model and the scene, predicting NOC values is sufficient for computing the transformation between local points from one observation to another.…”

Section: Related Workmentioning

confidence: 99%

DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-Based Robotic Grasping

2020

View full text Add to dashboard Cite

This article presents a method for grasping novel objects by learning from experience. Successful attempts are remembered and then used to guide future grasps such that more reliable grasping is achieved over time. To transfer the learned experience to unseen objects, we introduce the dense geometric correspondence matching network (DGCM-Net). This applies metric learning to encode objects with similar geometry nearby in feature space. Retrieving relevant experience for an unseen object is thus a nearest neighbor search with the encoded feature maps. DGCM-Net also reconstructs 3D-3D correspondences using the view-dependent normalized object coordinate space to transform grasp configurations from retrieved samples to unseen objects. In comparison to baseline methods, our approach achieves an equivalent grasp success rate. However, the baselines are significantly improved when fusing the knowledge from experience with their grasp proposal strategy. Offline experiments with a grasping dataset highlight the capability to transfer grasps to new instances as well as to improve success rate over time from increasing experience. Lastly, by learning task-relevant grasps, our approach can prioritize grasp configurations that enable the functional use of objects.

show abstract

CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation

Cited by 393 publications

References 17 publications

EPOS: Estimating 6D Pose of Objects With Symmetries

EPOS: Estimating 6D Pose of Objects With Symmetries

Toward Augmented Reality in Museums: Evaluation of Design Choices for 3D Object Pose Estimation

DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-Based Robotic Grasping

Contact Info

Product

Resources

About