CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

Abstract

While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc. Orthogonal to them, this work presents a category-level object pose and size refiner CATRE, which is able to iteratively enhance pose estimate from point clouds to produce accurate results. Given an initial pose estimate, CATRE predicts a relative transformation between the initial pose and ground truth by means of aligning the partially observed point cloud and an abstract shape prior. In specific, we propose a novel disentangled architecture being aware of the inherent distinctions between rotation and translation/size estimation. Extensive experiments show that our approach remarkably outperforms state-ofthe-art methods on REAL275, CAMERA25, and LM benchmarks up to a speed of ≈85.32Hz, and achieves competitive results on categorylevel tracking. We further demonstrate that CATRE can perform pose refinement on unseen category. Code and trained models are available. 1 * Equal contribution.

AG-Net: Category-level 6D Pose Estimation Network Based on Attention Mechanism and Global Enhancement

“…To validate the effectiveness of AG-Net, we conduct comparative experiments on both the CAMERA25 and REAL275 datasets with existing methods including those that utilize prior information [17,32,33,[37][38][39][40][41][42][43][44] and those that do not utilize prior information [8,9,13,31,34,45,46].…”

“…Quantitative comparison of various methods for category-level 6D pose estimation on the REAL275 datasets. '*' denotes the IoU metric from CATRE[39]. Bold indicates the best results, and underlining indicates the second-best results.…”