PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving
This work addresses safety issues in camera-only autonomous driving perception by improving panoptic 3D scene reconstruction, though it is incremental as it builds on existing occupancy networks.
The paper tackles inconsistent and mixed predictions in monocular 3D occupancy networks for autonomous driving by proposing PanoSSC, an instance-aware network that unifies geometric reconstruction, semantic segmentation, and instance segmentation, achieving competitive results on the SemanticKITTI benchmark.
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.