PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving

TL;DR

PanoSSC introduces an instance-aware occupancy network for monocular 3D scene reconstruction in autonomous driving, improving object segmentation and safety-critical environment understanding.

Contribution

It unifies geometric, semantic, and instance segmentation in a novel framework with a new 3D instance mask decoder and evaluation metrics.

Findings

Achieves competitive results on SemanticKITTI benchmark.

Effectively separates foreground objects from background.

Improves consistency and accuracy of 3D scene reconstruction.

Abstract

Vision-centric occupancy networks, which represent the surrounding environment with uniform voxels with semantics, have become a new trend for safe driving of camera-only autonomous driving perception systems, as they are able to detect obstacles regardless of their shape and occlusion. Modern occupancy networks mainly focus on reconstructing visible voxels from object surfaces with voxel-wise semantic prediction. Usually, they suffer from inconsistent predictions of one object and mixed predictions for adjacent objects. These confusions may harm the safety of downstream planning modules. To this end, we investigate panoptic segmentation on 3D voxel scenarios and propose an instance-aware occupancy network, PanoSSC. We predict foreground objects and backgrounds separately and merge both in post-processing. For foreground instance grouping, we propose a novel 3D instance mask decoder that can efficiently extract individual objects. we unify geometric reconstruction, 3D semantic segmentation, and 3D instance segmentation into PanoSSC framework and propose new metrics for evaluating panoptic voxels. Extensive experiments show that our method achieves competitive results on SemanticKITTI semantic scene completion benchmark.