Depth recovery via decomposition of polynomial and piece-wise constant signals

Xinchen Ye, Xiaolin Song, Jingyu Yang, Chunping Hou, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a novel decomposition model for high-quality depth recovery (DMDR) from low quality depth measurement accompanied by high-resolution RGB image. We observe that depth patches extracted from the depth map containing smooth regions separated by curves, can be decomposed simultaneously by a low-order polynomial surface and a piece-wise constant signal. In our model, the polynomial surface component is regularized by least-square polynomial smoothing, while the piece-wise constant component is constrained by total variation filtering. The model is effectively solved by the alternating direction method under the augmented Lagrangian multiplier (ALM-ADM) algorithm. Experimental results show that our method is able to handle various types of depth degradation under the designed signal decomposition model, and produces high-quality depth recovery results.

Original languageEnglish (US)
Title of host publicationVCIP 2016 - 30th Anniversary of Visual Communication and Image Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509053162
DOIs
StatePublished - Jan 4 2017
Event2016 IEEE Visual Communication and Image Processing, VCIP 2016 - Chengdu, China
Duration: Nov 27 2016Nov 30 2016

Publication series

NameVCIP 2016 - 30th Anniversary of Visual Communication and Image Processing

Other

Other2016 IEEE Visual Communication and Image Processing, VCIP 2016
CountryChina
CityChengdu
Period11/27/1611/30/16

Keywords

  • Depth recovery
  • Total variation
  • decomposition
  • piece-wise constant
  • polynomial

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Depth recovery via decomposition of polynomial and piece-wise constant signals'. Together they form a unique fingerprint.

Cite this