Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion

TL;DR

This paper introduces ScanSSC, a novel camera-based semantic scene completion model that enhances distant scene geometry by using axis-wise masked attention and a specialized loss, significantly improving accuracy in autonomous driving scenarios.

Contribution

The paper presents a new model, ScanSSC, with a scan module and scan loss that effectively improve distant scene understanding in camera-based SSC tasks.

Findings

Achieves state-of-the-art IoUs of 44.54 and 48.29 on SemanticKITTI and SSCBench-KITTI-360.

Utilizes axis-wise masked attention for better distant voxel relationship modeling.

Employs a cross-entropy scan loss to propagate context-aware signals to distant voxels.

Abstract

Camera-based Semantic Scene Completion (SSC) is gaining attentions in the 3D perception field. However, properties such as perspective and occlusion lead to the underestimation of the geometry in distant regions, posing a critical issue for safety-focused autonomous driving systems. To tackle this, we propose ScanSSC, a novel camera-based SSC model composed of a Scan Module and Scan Loss, both designed to enhance distant scenes by leveraging context from near-viewpoint scenes. The Scan Module uses axis-wise masked attention, where each axis employing a near-to-far cascade masking that enables distant voxels to capture relationships with preceding voxels. In addition, the Scan Loss computes the cross-entropy along each axis between cumulative logits and corresponding class distributions in a near-to-far direction, thereby propagating rich context-aware signals to distant voxels. Leveraging the synergy between these components, ScanSSC achieves state-of-the-art performance, with IoUs of 44.54 and 48.29, and mIoUs of 17.40 and 20.14 on the SemanticKITTI and SSCBench-KITTI-360 benchmarks.