Skip to main navigation Skip to search Skip to main content

Monocular Depth by NonLinear Diffusion

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth relationships of depicted objects. According to Kanizsa, mechanisms called amodal and modal completion permit to transform these local relative depth cues into a global depth reconstruction. In this paper, we propose a mathematical and computational translation of gestalt depth perception theory, from the detection of local depth cues to their synthesis into a consistent global depth perception. The detection of local depth cues is built on the response of a line segment detector (LSD), which works in a linear time relative to the image size without any parameter tuning. The depth synthesis process is based on the use of a nonlinear iterative filter which is asymptotically equivalent to the Perona-Malik partial differential equation (PDE). Experimental results are shown on several real images and demonstrate that this simple approach can account a variety of phenomena such as visual completion, transparency and self-occlusion.©2008 IEEE.
Original languageEnglish
Title of host publicationProceedings - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008
Pages95-102
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008 - Bhubaneswar, India
Duration: 16 Dec 200819 Dec 2008

Publication series

NameProceedings - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008

Conference

Conference6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008
PlaceIndia
CityBhubaneswar
Period16/12/0819/12/08

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Fingerprint

Dive into the research topics of 'Monocular Depth by NonLinear Diffusion'. Together they form a unique fingerprint.

Cite this