HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation

2025/10/11 by Yulin Wang, Mengting Hu, Wang, Yulin +5
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Robot Manipulation and Learning #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2510.10177

openalex publication_date 2025/10/11 · openalex created_date 2025/10/15 · openalex updated_date 2026/07/28

Abstract

In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current methods primarily focus on more efficient encoding techniques to improve the precision of predicted 3D coordinates on the object's front surface, overlooking the potential benefits of incorporating the back surface and interior of the object. To better utilize the full surface and interior of the object, this study predicts 3D coordinates of both the object's front and back surfaces and densely samples 3D coordinates between them. This process creates ultra-dense 2D-3D correspondences, effectively enhancing pose estimation accuracy based on the Perspective-n-Point (PnP) algorithm. Additionally, we propose Hierarchical Continuous Coordinate Encoding (HCCE) to provide a more accurate and efficient representation of front and back surface coordinates. Experimental results show that, compared to existing state-of-the-art (SOTA) methods on the BOP website, the proposed approach outperforms across seven classic BOP core datasets. Code is available at https://github.com/WangYuLin-SEU/HCCEPose.

Citations

• Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking
• RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images
• BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects
• FoundationPose-TensorRT
• BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects
• MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
• StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS
• An Adjustable Farthest Point Sampling Method for Approximately-sorted Point Cloud Data
• Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
• ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
• 6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An\n Accessible Dataset and Benchmark
• Occlusion-Robust Object Pose Estimation with Holistic Representation
• RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
• BOP Challenge 2020 on 6D Object Localization
• HybridPose: 6D Object Pose Estimation under Hybrid Representations
• CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose\n Estimation
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
• Understanding the Limitations of CNN-based Absolute Camera Pose\n Regression
• DPOD: 6D Pose Object Detector and Refiner
• Photorealistic Image Synthesis for Object Instance Detection
• Normalized Object Coordinate Space for Category-Level 6D Object Pose and\n Size Estimation
• PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
• Estimating 6D Pose From Localizing Designated Surface Keypoints
• BOP: Benchmark for 6D Object Pose Estimation
• Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image
• Real-Time Seamless Single Shot 6D Object Pose Prediction
• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
• BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
• Geometric Loss Functions for Camera Pose Regression with Deep Learning
• T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects
• Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd
• Deep Residual Learning for Image Recognition
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• Microsoft COCO: Common Objects in Context

Related

• Neural Correspondence Field for Object Pose Estimation
• CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network
• ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation
• 3D Human Pose Estimation = 2D Pose Estimation + Matching
• Absolute Human Pose Estimation with Depth Prediction Network