Synthetic Depth Image-Based Category-Level Object Pose Estimation With Effective Pose Decoupling and Shape Optimization

Category-level object pose estimation is a crucial task in the field of computer vision and finds numerous applications. However, the presence of unknown objects, significant shape, and scale variations within the same category pose challenges in this task. To address these challenges and achieve efficient and accurate category-level object pose estimation, we present EffectPose in this article. We first observe that objects of the same category often possess similar key regions, such as handles on cups. These key regions can establish correspondences for spatial poses, enabling pose estimation. To facilitate this, we employ a segmentation network to divide point clouds into multiple parts and map them to a shared latent space. Subsequently, by considering the correspondences between predicted implicit models and real point clouds for various key regions, we accomplish pose estimation. Since real object point clouds are typically dense and contain outliers, we propose a novel point cloud sampling network that can accurately select representative points for efficient correspondence construction. Furthermore, we decouple the scale and pose of objects based on the SIM(3) invariant descriptor and propose an online pose optimization method using this descriptor. This method enables online prediction and optimization of poses. Finally, to enhance pose estimation accuracy, we introduce a distance-weighted pose optimization method for pose refinement and adjustment. Experimental results demonstrate that our proposed method achieves efficient pose estimation and generalization by utilizing only synthetic depth images and a minimal number of network parameters, surpassing the performance of most existing methods.

• Publication year

  2024

• Venue

  IEEE Transactions on Instrumentation and Measurement

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TIM.2024.3427799
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GPT-COPE: A Graph-Guided Point Transformer for Category-Level Object Pose Estimation

  2024cited by this paper
• HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

  2023cited by this paper
• 6-D Object Pose Estimation Using Multiscale Point Cloud Transformer

  2023cited by this paper
• Generative Category-Level Shape and Pose Estimation with Semantic Primitives

  2022cited by this paper
• Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset

  2022cited by this paper
• Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation

  2022cited by this paper
• Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation

  2022cited by this paper
• E2EK: End-to-End Regression Network Based on Keypoint for 6D Pose Estimation

  2022cited by this paper
• Learning to Sample

  2022cited by this paper
• CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

  2022cited by this paper
• GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

  2022cited by this paper
• EANet: Edge-Attention 6D Pose Estimation Network for Texture-Less Objects

  2022cited by this paper
• Fast Point Cloud Sampling Network

  2022cited by this paper
• DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency

  2021cited by this paper
• SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

  2021cited by this paper
• SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation

  2021influential reference
• Real-Time and Efficient 6-D Pose Estimation From a Single RGB Image

  2021cited by this paper
• Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks

  2021cited by this paper
• FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism

  2021influential reference
• FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

  2021cited by this paper
• DualSDF: Semantic Shape Manipulation Using a Two-Level Representation

  2020influential reference
• Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

  2020cited by this paper
• G2L-Net: Global to Local Network for Real-Time 6D Pose Estimation With Embedding Vector Features

  2020cited by this paper
• Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation

  2020influential reference
• Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence

  2020cited by this paper
• Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis

  2020cited by this paper
• DPOD: 6D Pose Object Detector and Refiner

  2019cited by this paper
• DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

  2019cited by this paper
• Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

  2019influential reference
• SampleNet: Differentiable Point Cloud Sampling

  2019cited by this paper
• PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation

  2019influential reference
• ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape

  2018cited by this paper
• Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation

  2018cited by this paper
• PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation

  2018cited by this paper
• Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images

  2017cited by this paper
• Mask R-CNN

  2017cited by this paper
• SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again

  2017cited by this paper
• BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth

  2017cited by this paper
• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

  2017cited by this paper
• Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image

  2016cited by this paper
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

  2016cited by this paper
• Pyramid Scene Parsing Network

  2016cited by this paper
• SSD: Single Shot MultiBox Detector

  2015cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• 3D ShapeNets: A deep representation for volumetric shapes

  2014influential reference
• Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

  1991cited by this paper
• Parameters

  1965cited by this paper

• A Global–Local Network for Human Pose Estimation With Completed mmWave Radar Point Clouds

  2026cites this paper
• Point–Line Pose Estimation With a Known Direction by Branch-and-Bound Optimization

  2026cites this paper
• Dual-Path CNN–BiLSTM for mmWave-Based Human Skeletal Pose Estimation

  2025cites this paper
• SE(3)-Equivariance Learning for Category-Level Object Pose Estimation

  2025influential citation
• From visual understanding to 6D pose reconstruction: A cutting-edge review of deep learning-based object pose estimation

  2025cites this paper