Towards Confidence-guided Shape Completion for Robotic Applications

TL;DR

This paper introduces a confidence-guided, implicit 3D shape completion method that allows for high-resolution reconstructions at inference time, improving robotic perception and manipulation in unstructured environments.

Contribution

It presents a novel implicit shape completion approach with confidence estimation and a gradient-based sampling method for arbitrary resolution at inference time.

Findings

Outperforms state-of-the-art in shape accuracy

Enables high-resolution reconstructions without increased training complexity

Improves robotic grasping performance in experiments

Abstract

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only provide incomplete information due to limited workspaces, clutter or object self-occlusion. In recent years, deep learning architectures for shape completion have begun taking traction as effective means of inferring a complete 3D object representation from partial visual data. Nevertheless, most of the existing state-of-the-art approaches provide a fixed output resolution in the form of voxel grids, strictly related to the size of the neural network output stage. While this is enough for some tasks, e.g. obstacle avoidance in navigation, grasping and manipulation require finer resolutions and simply scaling up the neural network outputs is computationally expensive. In this paper, we address this limitation by proposing an object shape completion method based on an implicit 3D representation providing a confidence value for each reconstructed point. As a second contribution, we propose a gradient-based method for efficiently sampling such implicit function at an arbitrary resolution, tunable at inference time. We experimentally validate our approach by comparing reconstructed shapes with ground truths, and by deploying our shape completion algorithm in a robotic grasping pipeline. In both cases, we compare results with a state-of-the-art shape completion approach.