ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation
This work addresses a bottleneck in 6D pose estimation for robotics and AR/VR applications, but it is incremental as it builds on existing reconstruction-based methods.
The paper tackles the problem of improving reconstruction quality in category-level 6D object pose estimation by proposing ACR-Pose, a network that uses adversarial training to generate realistic canonical representations, achieving state-of-the-art performance on NOCS-CAMERA and NOCS-REAL datasets.
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.