论文标题
体素的语言接地
Voxel-informed Language Grounding
论文作者
论文摘要
自然2D图像应用的自然语言从根本上描述了3D世界。我们介绍了Voxel信息接地器（VLG），该语言接地模型以使用体积重建模型从视觉输入得出的体素图的形式利用3D几何信息。我们表明，VLG显着提高了对象参考游戏任务SNARE的接地精度。在撰写本文时，VLG在SNARE排行榜上排名最高，以2.0％的绝对提高获得SOTA结果。
Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.
