期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 7, 期 4, 页码 9597-9604出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3189792
关键词
RGB-D perception; deep learning for visual perception
类别
资金
- Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation
This paper presents a modular pipeline for pose and shape estimation of objects from RGB-D images. The method incorporates a generative shape model, an initialization network, and a differentiable renderer to enable accurate estimation of 6D pose and shape from single or multiple views. The use of discretized signed distance fields as a shape representation is investigated and proved to be efficient.
Rich geometric understanding of the world is an important component of many robotic applications such as planning and manipulation. In this paper, we present a modular pipeline for pose and shape estimation of objects from RGB-D images given their category. The core of our method is a generative shape model, which we integrate with a novel initialization network and a differentiable renderer to enable 6D pose and shape estimation from a single or multiple views. We investigate the use of discretized signed distance fields as an efficient shape representation for fast analysis-by-synthesis optimization. Our modular framework enables multi-view optimization and extensibility. We demonstrate the benefits of our approach over state-of-the-art methods in several experiments on both synthetic and real data. We open-source our approach at https://github.com/roym899/sdfest.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据