Event-Aided Semantic Scene Completion

Résumé fourni par la source

Recent advances in Semantic Scene Completion (SSC) for autonomous driving underscore the limitations of RGB-based approaches, which struggle under motion blur, poor lighting, and adverse weather. Event cameras, offering high dynamic range and low latency, address these challenges by providing asynchronous data that complements RGB inputs. We present DSEC-SSC, the first real-world benchmark specifically designed for event-aided SSC, which includes a novel 4D labeling pipeline for generating dense, visibility-aware labels that adapt dynamically to object motion. Our proposed RGB-Event fusion framework, EvSSC, introduces an Event-aided Lifting Module (ELM) that effectively bridges 2D RGB-Event features to 3D space, enhancing view transformation across SSC models. Evaluations on DSEC-SSC and simulated SemanticKITTI-E show that EvSSC is adaptable to both transformer-based and LSS-based SSC architectures, achieving up to a 52.5% relative improvement in mIoU under degraded conditions on the corrupted SemanticKITTI-C dataset. The established datasets and our codebase will be made publicly available at https://github.com/Pandapan01/EvSSC.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.