Preprint Article Version 1 This version is not peer-reviewed

Double Refinement Network for Room Layout Estimation

Version 1 : Received: 20 May 2019 / Approved: 22 May 2019 / Online: 22 May 2019 (08:58:09 CEST)

How to cite: Kruzhilov, I.; Romanov, M.; Konushin, A. Double Refinement Network for Room Layout Estimation. Preprints 2019, 2019050270 (doi: 10.20944/preprints201905.0270.v1). Kruzhilov, I.; Romanov, M.; Konushin, A. Double Refinement Network for Room Layout Estimation. Preprints 2019, 2019050270 (doi: 10.20944/preprints201905.0270.v1).

Abstract

Layout estimation is a challenge of segmenting a cluttered room image into floor, walls and ceiling. We applied Double refinement network proved to be efficient in the depth estimation to generate heat maps for room key points and edges. Our method is the first not using encoder-decoder architecture for the room layout estimation. ResNet50 was utilized as a backbone for the network instead of VGG16 commonly used for the task, allowing the network to be more compact and faster. We designed a special layout score function and layout ranking algorithm for key points and edges output. Our method achieved the lowest pixel and corner errors on the LSUN data set. The input image resolution is 224*224.

Subject Areas

layout estimation; depth; neural network; LSUN; room layout

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.