arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07466cs.CV
收藏

三维语义场景自动完成技术综述

3D Semantic Scene Completion: a Survey

Inria(法国国家信息与自动化研究所);AKKA Research(AKKA研究院)

Luis Roldao, Raoul de Charette, Anne Verroust-Blondet

摘要:

语义场景完成(SSC)的目的是联合估计完整的几何和语义的场景,假设部分稀疏输入。在过去几年中,随着大规模3D数据集的增加,SSC在研究界获得了巨大的发展势头,因为它面临着尚未解决的挑战。具体而言,SSC在于大面积未观测区域的完成不明确和地面实况的监督信号弱。这导致关于这一问题的论文数量大幅增加。这项调查的目的是确定,比较和分析的技术提供了一个关键的分析SSC文献的方法和数据集。在整个论文中,我们对现有的作品进行了深入的分析,涵盖了作者所做的所有选择,同时强调了剩余的研究途径。最流行的数据集上的SoA的SSC性能也进行了评估和分析。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑