3D Semantic Scene Completion: a Survey

TL;DR

This survey reviews recent advances in 3D Semantic Scene Completion, analyzing methods, datasets, and performance, while highlighting unresolved challenges and future research directions in the field.

Contribution

It provides a comprehensive comparison and critical analysis of existing SSC techniques and datasets, identifying gaps and future research avenues.

Findings

State-of-the-art methods show promising results on popular datasets.

Current challenges include unobserved area completion and weak supervision signals.

Performance varies significantly across different datasets and techniques.

Abstract

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.