CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration

TL;DR

This paper introduces CORSAIR, a novel method for online object mapping that combines convolutional features, object retrieval, and symmetry-aware registration to improve robustness in unknown environments.

Contribution

We extend the Fully Convolutional Geometric Features model to include global shape embeddings and symmetry-aware local feature matching for improved object registration.

Findings

Effective in synthetic and real-world datasets

Robust to object symmetries and partial observations

Outperforms existing methods in object registration accuracy

Abstract

This paper considers online object-level mapping using partial point-cloud observations obtained online in an unknown environment. We develop and approach for fully Convolutional Object Retrieval and Symmetry-AIded Registration (CORSAIR). Our model extends the Fully Convolutional Geometric Features model to learn a global object-shape embedding in addition to local point-wise features from the point-cloud observations. The global feature is used to retrieve a similar object from a category database, and the local features are used for robust pose registration between the observed and the retrieved object. Our formulation also leverages symmetries, present in the object shapes, to obtain promising local-feature pairs from different symmetry classes for matching. We present results from synthetic and real-world datasets with different object categories to verify the robustness of our method.