Segmentation-driven 6D Object Pose Estimation

Hu, Yinlin; Hugonot, Joachim; Fua, Pascal; Salzmann, Mathieu

doi:10.48550/arxiv.1812.02541

Cited by 3 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table III and IV compare our method with [5], [9], [10], [12], [13] on the more challenging YCB-Video dataset. For fair comparisons, we use the segmentation masks from [5] and [13].…”

Section: F Comparison On Ycb-videomentioning

confidence: 99%

“…The recent explosion in 6D object pose estimation is arguably a result of the application of deep neural networks. Many proposed deep networks [3]- [10] only leverage RGB data, which are inherently sensitive to changing lighting conditions [11] and object appearance variations [6]. To mitigate these problems, researchers start to take advantage of 3D geometric features and use RGB-D images for object pose estimation.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, performance on occluded objects are not satisfactory. To address the occlusion problem, dense prediction methods [5], [7]- [10] are proposed. [9] and [10] estimate a pose at each visible local patch independently, and accumulate results over all patches.…”

Section: Introductionmentioning

confidence: 99%

“…To address the occlusion problem, dense prediction methods [5], [7]- [10] are proposed. [9] and [10] estimate a pose at each visible local patch independently, and accumulate results over all patches. [5] and [7] predict a unit vector at each pixel pointing towards keypoints.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust 6D Object Pose Estimation by Learning RGB-D Features

Tian

Pan

Ang

et al. 2020

Preprint

View full text Add to dashboard Cite

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of symmetric objects. In this work, we propose a novel discretecontinuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Additionally, the object location is detected by aggregating point-wise vectors pointing to the 3D center. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches. Our code is available at https://github.com/ mentian/object-posenet.

show abstract

“…Table III and IV compare our method with [5], [9], [10], [12], [13] on the more challenging YCB-Video dataset. For fair comparisons, we use the segmentation masks from [5] and [13].…”

Section: F Comparison On Ycb-videomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust 6D Object Pose Estimation by Learning RGB-D Features

Tian

Pan

Ang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Some approaches rely on depth sensors and exploit the depth information which is essential for 6D pose estimation [41,34,15,40,37]. Other approaches use monocular RGB images to estimate the 6D pose of an object where the problem can be more challenging [17,28,38,43,27].…”

Section: Introductionmentioning

confidence: 99%

Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction

Castro

Armagan

Kim

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Current 6D object pose methods consist of deep CNN models fully optimized for a single object but with its architecture standardized among objects with different shapes. In contrast to previous works, we explicitly exploit each object's distinct topological information i.e. 3D dense meshes in the pose estimation model, with an automated process and prior to any post-processing refinement stage. In order to achieve this, we propose a learning framework in which a Graph Convolutional Neural Network reconstructs a pose conditioned 3D mesh of the object. A robust estimation of the allocentric orientation is recovered by computing, in a differentiable manner, the Procrustes' alignment between the canonical and reconstructed dense 3D meshes. 6D egocentric pose is then lifted using additional mask and 2D centroid projection estimations. Our method is capable of self validating its pose estimation by measuring the quality of the reconstructed mesh, which is invaluable in real life applications. In our experiments on the LINEMOD, OCCLUSION and YCB-Video benchmarks, the proposed method outperforms state-of-the-arts.

show abstract

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Salzmann³

et al. 2021

AAAI

Self Cite

View full text Add to dashboard Cite

The current leading 6D object pose estimation methods rely heavily on annotated real data, which is highly costly to acquire. To overcome this, many works have proposed to introduce computer-generated synthetic data. However, bridging the gap between the synthetic and real data remains a severe problem. Images depicting different levels of realism/semantics usually have different transferability between the synthetic and real domains. Inspired by this observation, we introduce an approach, SD-Pose, that explicitly decomposes the input image into multi-level semantic representations and then combines the merits of each representation to bridge the domain gap. Our comprehensive analyses and experiments show that our semantic decomposition strategy can fully utilize the different domain similarities of different representations, thus allowing us to outperform the state of the art on modern 6D object pose datasets without accessing any real data during training.

show abstract

Segmentation-driven 6D Object Pose Estimation

Cited by 3 publications

References 42 publications

Robust 6D Object Pose Estimation by Learning RGB-D Features

Robust 6D Object Pose Estimation by Learning RGB-D Features

Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Contact Info

Product

Resources

About