SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fields
This work addresses geometric understanding for robotic applications like planning and manipulation, but it is incremental as it builds on existing methods with modular improvements.
The paper tackles the problem of 6D pose and shape estimation of objects from RGB-D images by proposing a modular pipeline that integrates a generative shape model with a novel initialization network and differentiable renderer, achieving benefits over state-of-the-art methods in experiments on synthetic and real data.
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.