MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

arXiv:2403.08019v1 Announce Type: new
Abstract: We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between …

3d object abstract arxiv cad classification computer correlation cs.cv design image object residual type