Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Dave Zhenyu Chen, Ali Gholami, Matthias Nießner, Angel X. Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

44 Scopus citations

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 underlying objects. To address the 3D object detection and description problems, we propose Scan2Cap, an end-to-end trained method, to detect objects in the input scene and describe them in natural language. We use an attention mechanism that generates descriptive tokens while referring to the related components in the local context. To reflect object relations (i.e. relative spatial relations) in the generated captions, we use a message passing graph module to facilitate learning object relation features. Our method can effectively localize and describe 3D objects in scenes from the ScanRefer dataset, outperforming 2D baseline methods by a significant margin (27.61% [email protected] improvement).

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PublisherIEEE Computer Society
Pages3192-3202
Number of pages11
ISBN (Electronic)9781665445092
DOIs
StatePublished - 2021
Event2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States
Duration: 19 Jun 202125 Jun 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Country/TerritoryUnited States
CityVirtual, Online
Period19/06/2125/06/21

Fingerprint

Dive into the research topics of 'Scan2Cap: Context-aware Dense Captioning in RGB-D Scans'. Together they form a unique fingerprint.

Cite this