Litcius/Paper detail

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

Zhaoxin Fan, Zhenbo Song, Zhicheng Wang, Jian Hui Xu, Kejian Wu, Hongyan Liu, Jun He

202415 citationsDOIOpen Access PDF

Abstract

In the realm of category-level 6D object pose estimation, canonical 3D representation reconstruction is pivotal, yet current methods show limitations in reconstruction quality, a key step in current pose estimation pipeline. To address this, we introduce an innovative Adversarial Canonical Representation Reconstruction Network (ACR-Pose) in this paper. In particular, ACR-Pose comprises a Reconstructor, with novel sub-modules: a Pose-Irrelevant Module (PIM) for robustness to rotation and translation, and a Relational Reconstruction Module (RRM) for extracting relational information between input modalities. A Discriminator is incorporated to guide the generation of realistic canonical representations through adversarial optimization. Evaluated on the prevalent NOCS-CAMERA and NOCS-REAL datasets, our method significantly improves the performance of baseline models and achieves comparable performance with existing state-of-the-art methods, representing a promising advancement in the field of category-level 6D object pose estimation.

Topics & Concepts

PoseAdversarial systemArtificial intelligenceComputer scienceRepresentation (politics)Computer visionObject (grammar)3D pose estimationArticulated body pose estimationPattern recognition (psychology)Political sciencePoliticsLawRobot Manipulation and LearningAdversarial Robustness in Machine LearningImage and Object Detection Techniques