CVNov 18, 2023

SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation

arXiv:2311.11125v366 citationsh-index: 58
Originality Incremental advance
AI Analysis

This work addresses a key challenge in robotics and computer vision for applications like manipulation and AR/VR, offering a significant but incremental advance over prior methods.

The paper tackles the problem of category-level object pose estimation, which struggles with large intra-class shape variation, by introducing SecondPose, a method that integrates object-specific geometric features with semantic category priors from DINOv2, achieving a 12.4% improvement over state-of-the-art on NOCS-REAL275 and outperforming competitors on HouseCat6D.

Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes