BriefGPT.xyz
Dec, 2020
Scan2Cap：RGB-D扫描中基于上下文的密集字幕生成
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
HTML
PDF
Dave Zhenyu Chen, Ali Gholami, Matthias Nießner, Angel X. Chang
TL;DR
本文介绍了使用Scan2Cap方法对3D扫描中的物体进行检测和描述，在生成的描述中使用注意力机制和消息传递图模块，取得了显著的性能提升。
Abstract
We introduce the task of
dense captioning
in
3d scans
from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the u
→