ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation

2021/11/20 by Zhaoxin Fan, Zhengbo Song, Fan, Zhaoxin +11 · 1 citation
Engineering · #3D Shape Modeling and Analysis #Anatomy and Medical Technology #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robot Manipulation and Learning

paper · pdf · doi:10.48550/arxiv.2111.10524

openalex publication_date 2021/11/20 · openalex created_date 2021/12/06 · openalex updated_date 2026/07/28

Abstract

Recently, category-level 6D object pose estimation has achieved significant improvements with the development of reconstructing canonical 3D representations. However, the reconstruction quality of existing methods is still far from excellent. In this paper, we propose a novel Adversarial Canonical Representation Reconstruction Network named ACR-Pose. ACR-Pose consists of a Reconstructor and a Discriminator. The Reconstructor is primarily composed of two novel sub-modules: Pose-Irrelevant Module (PIM) and Relational Reconstruction Module (RRM). PIM tends to learn canonical-related features to make the Reconstructor insensitive to rotation and translation, while RRM explores essential relational information between different input modalities to generate high-quality features. Subsequently, a Discriminator is employed to guide the Reconstructor to generate realistic canonical representations. The Reconstructor and the Discriminator learn to optimize through adversarial training. Experimental results on the prevalent NOCS-CAMERA and NOCS-REAL datasets demonstrate that our method achieves state-of-the-art performance.

Citations

• A Survey of Augmented Reality
• YOLOv3: An Incremental Improvement
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting

Cited by

• THE-Pose: Topological Prior with Hybrid Graph Fusion for Estimating Category-Level 6D Object Pose

Related

• Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks
• NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
• Single-Stage 6D Object Pose Estimation
• Object Pose Estimation using Mid-level Visual Representations
• FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism