Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robots
This addresses the challenge of out-of-distribution scenarios in robotic perception, enabling more precise object manipulation, though it is incremental as it builds on existing segmentation and reconstruction methods.
The paper tackles the problem of inaccurate panoptic segmentation in 3D scene reconstruction for mobile robots by refining segmentation errors using kernel density estimation on depth maps, showing improvements in both synthetic and real-world tests.
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.