Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robots

TL;DR

This paper introduces a non-parametric statistical refinement method for improving 3D panoptic scene reconstruction in mobile robots, enhancing segmentation accuracy and robustness in out-of-distribution scenarios.

Contribution

It proposes a novel kernel density-based refinement technique for panoptic segmentation in 3D mapping, improving accuracy without additional parameters.

Findings

Significant improvement in segmentation quality on synthetic data

Effective outlier rejection in depth perception

Successful deployment on real-robot system

Abstract

Reconstructing three-dimensional (3D) scenes with semantic understanding is vital in many robotic applications. Robots need to identify which objects, along with their positions and shapes, to manipulate them precisely with given tasks. Mobile robots, especially, usually use lightweight networks to segment objects on RGB images and then localize them via depth maps; however, they often encounter out-of-distribution scenarios where masks over-cover the objects. In this paper, we address the problem of panoptic segmentation quality in 3D scene reconstruction by refining segmentation errors using non-parametric statistical methods. To enhance mask precision, we map the predicted masks into a depth frame to estimate their distribution via kernel densities. The outliers in depth perception are then rejected without the need for additional parameters in an adaptive manner to out-of-distribution scenarios, followed by 3D reconstruction using projective signed distance functions (SDFs). We validate our method on a synthetic dataset, which shows improvements in both quantitative and qualitative results for panoptic mapping. Through real-world testing, the results furthermore show our method's capability to be deployed on a real-robot system. Our source code is available at: https://github.com/mkhangg/refined panoptic mapping.