PanDepth: Joint Panoptic Segmentation and Depth Completion

TL;DR

PanDepth is a multi-task model that jointly performs panoptic segmentation and depth completion from RGB images and sparse depth data, achieving dense depth maps and segmentation with high accuracy and low computational cost.

Contribution

It introduces a novel multi-task framework that combines panoptic segmentation and depth completion, efficiently handling multiple scene understanding tasks simultaneously.

Findings

Successfully predicts dense depth maps from sparse inputs.

Performs accurate panoptic segmentation on each frame.

Operates with minimal increase in computational cost.

Abstract

Understanding 3D environments semantically is pivotal in autonomous driving applications where multiple computer vision tasks are involved. Multi-task models provide different types of outputs for a given scene, yielding a more holistic representation while keeping the computational cost low. We propose a multi-task model for panoptic segmentation and depth completion using RGB images and sparse depth maps. Our model successfully predicts fully dense depth maps and performs semantic segmentation, instance segmentation, and panoptic segmentation for every input frame. Extensive experiments were done on the Virtual KITTI 2 dataset and we demonstrate that our model solves multiple tasks, without a significant increase in computational cost, while keeping high accuracy performance. Code is available at https://github.com/juanb09111/PanDepth.git