no code implementations • 18 Nov 2020 • Christoph B. Rist, David Emmerichs, Markus Enzweiler, Dariu M. Gavrila
We show that this continuous representation is suitable to encode geometric and semantic properties of extensive outdoor scenes without the need for spatial discretization (thus avoiding the trade-off between level of scene detail and the scene extent that can be covered).
Ranked #5 on 3D Semantic Scene Completion on SemanticKITTI