PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion
This work addresses a gap in semantic scene completion for outdoor navigation by providing a new benchmark, but it is incremental as it builds on existing methods with a novel dataset.
The authors tackled the lack of outdoor point cloud benchmarks for semantic scene completion by introducing PointSSC, a cooperative vehicle-infrastructure dataset with automated semantic annotation, and proposed a LiDAR-based model that achieved competitive performance on this new benchmark.
Semantic Scene Completion (SSC) aims to jointly generate space occupancies and semantic labels for complex 3D scenes. Most existing SSC models focus on volumetric representations, which are memory-inefficient for large outdoor spaces. Point clouds provide a lightweight alternative but existing benchmarks lack outdoor point cloud scenes with semantic labels. To address this, we introduce PointSSC, the first cooperative vehicle-infrastructure point cloud benchmark for semantic scene completion. These scenes exhibit long-range perception and minimal occlusion. We develop an automated annotation pipeline leveraging Semantic Segment Anything to efficiently assign semantics. To benchmark progress, we propose a LiDAR-based model with a Spatial-Aware Transformer for global and local feature extraction and a Completion and Segmentation Cooperative Module for joint completion and segmentation. PointSSC provides a challenging testbed to drive advances in semantic point cloud completion for real-world navigation. The code and datasets are available at https://github.com/yyxssm/PointSSC.