Indoor scene understanding from RGB-D images

Saurabh Gupta, Pablo Arbeláez, Ross Girshick, Jitendra Malik

Research output: Contribution to journalConference articlepeer-review


Our goal is to be able to align objects in an RGB-D image with 3D models from a library. Our pipeline for this task involves detecting and segmenting objects and estimating coarse pose using a convolutional neural network, followed by inserting the rendered model in the scene.

Original languageEnglish (US)
Pages (from-to)87-90
Number of pages4
JournalDigest of Technical Papers - SID International Symposium
Issue numberBook 1
StatePublished - Jun 1 2015
Externally publishedYes
Event2015 SID International Symposium - San Jose, United States
Duration: Jun 2 2015Jun 3 2015

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Indoor scene understanding from RGB-D images'. Together they form a unique fingerprint.

Cite this