论文标题
CATRE：类别级对象姿势完善的迭代点云对齐
CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement
论文作者
论文摘要
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.鉴于初始姿势估计，Catre通过对齐部分观察到的点云和先验的抽象形状来预测初始姿势和地面真理之间的相对转换。具体而言，我们提出了一种新型的分离架构，以意识到旋转与翻译/大小估计之间的固有区别。广泛的实验表明，我们的方法在Real275，Camera25和LM基准测试的最先进方法上的表现非常优于〜85.32Hz的最新方法，并在类别级别跟踪上取得了竞争成果。我们进一步证明，Catre可以对看不见的类别进行姿势完善。可以使用代码和训练有素的模型。
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-of-the-art methods on REAL275, CAMERA25, and LM benchmarks up to a speed of ~85.32Hz, and achieves competitive results on category-level tracking. We further demonstrate that CATRE can perform pose refinement on unseen category. Code and trained models are available.
