DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
This addresses the problem of accurate 6D object pose estimation for robotics and computer vision applications, representing an incremental improvement with novel module designs.
The paper tackles the suboptimal learning in 6D pose estimation due to surrogate objectives in correspondence learning by introducing DCL-Net, which uses Feature Disengagement and Alignment modules to directly regress poses with confidence scores, resulting in outperforming existing methods on datasets like YCB-Video, LineMOD, and Oclussion-LineMOD.
Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence learning in 3D space are a step away from the true ones of object pose estimation, making the learning suboptimal for the end task. In this paper, we address this shortcoming by introducing a new method of Deep Correspondence Learning Network for direct 6D object pose estimation, shortened as DCL-Net. Specifically, DCL-Net employs dual newly proposed Feature Disengagement and Alignment (FDA) modules to establish, in the feature space, partial-to-partial correspondence and complete-to-complete one for partial object observation and its complete CAD model, respectively, which result in aggregated pose and match feature pairs from two coordinate systems; these two FDA modules thus bring complementary advantages. The match feature pairs are used to learn confidence scores for measuring the qualities of deep correspondence, while the pose feature pairs are weighted by confidence scores for direct object pose regression. A confidence-based pose refinement network is also proposed to further improve pose precision in an iterative manner. Extensive experiments show that DCL-Net outperforms existing methods on three benchmarking datasets, including YCB-Video, LineMOD, and Oclussion-LineMOD; ablation studies also confirm the efficacy of our novel designs.