3D Semantic Scene Completion: a Survey
It provides a comprehensive review for researchers in computer vision and robotics, identifying and comparing techniques to guide future work, but it is incremental as it synthesizes existing literature rather than introducing new methods.
This survey analyzes the field of 3D Semantic Scene Completion (SSC), which addresses the problem of jointly estimating complete geometry and semantics from partial sparse inputs, focusing on unresolved challenges like ambiguous completion and weak supervision.
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum in the research community because it holds unresolved challenges. Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. This led to a substantially increasing number of papers on the matter. This survey aims to identify, compare and analyze the techniques providing a critical analysis of the SSC literature on both methods and datasets. Throughout the paper, we provide an in-depth analysis of the existing works covering all choices made by the authors while highlighting the remaining avenues of research. SSC performance of the SoA on the most popular datasets is also evaluated and analyzed.