SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

Lin, Haitao; Liu, Zichang; Cheang, Chilam; Fu, Yanwei; Guo, Guodong; Xue, Xiangyang

doi:10.1109/cvpr52688.2022.00659

Cited by 49 publications

(17 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wen et al [33] introduce NUNOCS, which allows non-uniform scaling across three dimensions, facilitating fine-grained dense correspondences across object instances with large shape variations. Crucially, a bunch of recent works have adopted the categorical mean shape to facilitating the computation of correspondences between the observed points and their canonical coordinate [28,5,19]. Our method falls into the category of correspondence-based methods.…”

Section: Category-level Pose Estimationmentioning

confidence: 99%

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

Wan¹,

Shi²,

Xu³

2023

Preprint

View full text Add to dashboard Cite

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a category containing significant intra-category shape variations. This is because the object coordinates induced by global and rigid alignment of objects are semantically incoherent, making the coordinate regression hard to learn and generalize. We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-andaligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence. SOCS is semantically coherent: Any point on the surface of a object can be mapped to a semantically meaningful location in SOCS, allowing for accurate pose and size estimation under large shape variations. To learn effective coordinate regression to SOCS, we propose a novel multi-scale coordinate-based attention network. Evaluations demonstrate that our method is easy to train, well-generalizing for large intra-category shape variations and robust to inter-object occlusions.

show abstract

Section: Category-level Pose Estimationmentioning

confidence: 99%

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

Wan¹,

Shi²,

Xu³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…FS-Net [5] explored local geometric relationships using 3D-GC [23], which shows robustness to rotation estimation and runs in real-time. [7,20,55,56] inherit the utilization of 3D-GC and enhance the pose estimation performance in different ways. SAR-Net [20] proposes shape alignment and symmetry-aware shape reconstruction.…”

Section: Related Workmentioning

confidence: 99%

“…[7,20,55,56] inherit the utilization of 3D-GC and enhance the pose estimation performance in different ways. SAR-Net [20] proposes shape alignment and symmetry-aware shape reconstruction. GPV-Pose [7] presents geometric-pose consistency terms and point-wise bounding box (Bbox) voting.…”

Section: Related Workmentioning

confidence: 99%

“…[2,46] gain the ability to generalize by mapping the input shape to normalized or metric-scale canonical spaces and then recovering the objects' poses via correspondence matching. Better handling of intra-category shape variation is also achieved by leveraging shape priors [4,42,56], symmetry priors [20], or domain adaptation [17,21]. Additionally, [5] enhances the perceptiveness of local geometry, and [7,55] exploit geometric consistency terms to improve the performance further.…”

Section: Introductionmentioning

confidence: 99%

“…Reconstruction and matching-based methods [17,42,46] are usually limited in speed due to the time-consuming correspondencematching procedure. Recently, various methods [5,7,20,55,56] built on 3D graph convolution (3D-GC) [23] have achieved impressive performance and run in real-time. They show outstanding local geometric sensitivity and the ability to generalize to unseen objects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

Zheng¹,

Wang²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object's size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. The proposed HS-layer: 1) is able to perceive local-global geometric structure and global information, 2) is robust to noise, and 3) can encode size and translation information. Our experiments show that the simple replacement of the 3D-GC layer with the proposed HS-layer on the baseline method (GPV-Pose) achieves a significant improvement, with the performance increased by 14.5% on 5 • 2cm metric and 10.3% on IoU 75 . Our method outperforms the state-of-the-art methods by a large margin (8.3% on 5 • 2cm, 6.9% on IoU 75 ) on REAL275 dataset and runs in real-time (50 FPS) 1 .

show abstract

Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks

Lin

Wei

Ding

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

Cited by 49 publications

References 51 publications

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks

Contact Info

Product

Resources

About