6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics

Abstract

We present a novel technique to estimate the 6D pose of objects from single images where the 3D geometry of the object is only given approximately and not as a precise 3D model. To achieve this, we employ a dense 2D-to-3D correspondence predictor that regresses 3D model coordinates for every pixel. In addition to the 3D coordinates, our model also estimates the pixel-wise coordinate error to discard correspondences that are likely wrong. This allows us to generate multiple 6D pose hypotheses of the object, which we then refine iteratively using a highly efficient region-based approach. We also introduce a novel pixel-wise posterior formulation by which we can estimate the probability for each hypothesis and select the most likely one. As we show in experiments, our approach is capable of dealing with extreme visual conditions including overexposure, high contrast, or low signal-to-noise ratio. This makes it a powerful technique for the particularly challenging task of estimating the pose of tumbling satellites for in-orbit robotic applications. Our method achieves stateof-the-art performance on the SPEED+ dataset and has won the SPEC2021 post-mortem competition. Code, trained models, and the used satellite model will be made publicly available.

Spacecraft Homography Pose Estimation with Single-Stage Deep Convolutional Neural Network

“…SPEC2021 particularly emphasizes domain gaps where the source and target data distributions differ, while the tasks remain the same. We adopt a semi-supervised learning strategy [ 37 , 38 , 39 ]. Specifically, we randomly select a portion of the target dataset and annotate it in the format of coco [ 34 ].…”