V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communication
This addresses safety risks in autonomous navigation by improving perception through V2V collaboration, though it is incremental as it builds on existing datasets and methods.
The paper tackles occlusion and short-range perception in semantic scene completion (SSC) for autonomous vehicles by introducing a collaborative framework using vehicle-to-vehicle (V2V) communication, resulting in performance gains of 8.3% in geometric IoU and 6.0% in mIOU.
Semantic scene completion (SSC) has recently gained popularity because it can provide both semantic and geometric information that can be used directly for autonomous vehicle navigation. However, there are still challenges to overcome. SSC is often hampered by occlusion and short-range perception due to sensor limitations, which can pose safety risks. This paper proposes a fundamental solution to this problem by leveraging vehicle-to-vehicle (V2V) communication. We propose the first generalized collaborative SSC framework that allows autonomous vehicles to share sensing information from different sensor views to jointly perform SSC tasks. To validate the proposed framework, we further build V2VSSC, the first V2V SSC benchmark, on top of the large-scale V2V perception dataset OPV2V. Extensive experiments demonstrate that by leveraging V2V communication, the SSC performance can be increased by 8.3% on geometric metric IoU and 6.0% mIOU.