Semi-automatic 2D to 3D image conversion using a hybrid Random Walks and graph cuts based approach

Phan, Raymond; Rzeszutek, Richard; Androutsos, Dimitrios

doi:10.1109/icassp.2011.5946549

Cited by 12 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need for this type of depth estimation was driven, primarily, by the author's prior work in 2D-to-3D image conversion [9,10,11]. Semi-automatic conversion is a relatively straightforward process as all it requires is that the user indicate the relative depths for different regions in a scene.…”

Section: Motivationmentioning

confidence: 99%

A framework for estimating relative depth in video

Rzeszutek¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This dissertation proposes a novel framework for recovering relative depth maps from a video. The framework is composed of two parts: a depth estimator and a sparse label interpolator. These parts are completely separate from one another and can operate independently. Prior methods have tended to heavily couple the interpolation stage with the depth estimation, which can assist with automation at the expense of flexibility. The loss of this flexibility can in fact be worse than any advantage gained by coupling the two stages together. This dissertation shows how by treating the two stages separately, it is very easy to change the quality of the results with little effort. It also leaves room for other adjustments. The depth estimator is based upon well-established computer vision principles and only has the restriction that the camera must be moving in order to obtain depth estimates. By starting from first principles, this dissertation has developed a new approach for quickly estimating relative depth. That is, it is able to answer the question, “is this feature closer than another," with relatively little computational overhead. The estimator is designed using a pipeline-style approach so that it produces sparse depth estimates in an online fashion; i.e. a depth estimate is automatically available for each new frame presented to the estimator. Finally, the interpolator applies an existing method based upon edge-aware filtering to generate the final depth maps. When temporal filters are used, the interpolation stage is able to very easily handle frames without any depth information, such as when the camera was stationary. However, unlike the prior work, this dissertation establishes the theoretical background for this type of interpolation and addresses some of the associated numerical problems. Strategies for dealing with these issues have also been provided

show abstract

Section: Motivationmentioning

confidence: 99%

A framework for estimating relative depth in video

Rzeszutek¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…User labelling such as in [41] provide an intuitive way for users to interact with the images; labels simply correspond to objects which users see and wish to segment. The labeling itself can also be used to assign the depth value to the segmentation, thereby serving a dual purpose such as in [42], [43] CHAPTER 1. INTRODUCTION & BACKGROUND…”

Section: Semi-automatic 2d To 3d Conversionmentioning

confidence: 99%

Adaptive 2D To 3D Image Conversion Using A Hybrid Graph Cuts And Random Walks Approach

Fawaz¹

2021

Preprint

View full text Add to dashboard Cite

This thesis proposes an adaptive method for 2D to 3D conversion of images using a user-aided process based on Graph Cuts and Random Walks. Given user-defined labelling that correspond to a rough estimate of depth, the system produces a depth map which, combined with a 2D image can be used to synthesize a stereoscopic image pair. The work presented here is an extension of work done previously combining the popular Graph Cuts and Random Walks image segmentation algorithms. Specifically, the previous approach has been made adaptive by removing empirically determined constants; as well the quality of the results has been improved. This is achieved by feeding information from the Graph Cuts result into the Random Walks process in two different ways, and using edge and spatial information to adapt various weights. This thesis also presents a practical application which allows for a user to go through the entire process of 2D to 3D conversion using the method proposed in this work. The application is written using MATLAB, and allows a user to generate and edit depth maps intuitively and also allows a user to synthesize additional views of the image for display on 3D capable devices.

show abstract

“…Phan et al [2], proposed a paper on 2-D to 3-D image conversion in which segmentation algorithms are used to generate a final cohesive depth map. The obtained results demonstration that we can produce good quality stereoscopic image pairs.…”

Section: Literature Surveymentioning

confidence: 99%

“…In second method (CID) we are able to convert a stable 2-D image into 3-D using two projections. While the third method is a combination of the earlier two methods for converting2-D image into 3-D image in Real-Time. Advantages of proposed system:  Low cost  Simple to use  Refined images  Easy for diagnosis 3.…”

mentioning

confidence: 99%

System to Convert 2-D X-Ray Image Into 3-D X-Ray Image in Dentistry

.¹

2014

IJRET

View full text Add to dashboard Cite

An X-Ray machine is used to capture the formation of bones and tissues by sending X-Ray particles through the body. Dental X-Rays help dentists envision infections of the teeth and adjacent tissue that cannot be seen with a simple oral test. In addition, X-Rays help the dentist discovery and treat dental complications early in their growth. But not all diseases can be detected by a 2-D X-Ray. This system is proposed to get a 3-D X-Ray image of the infected area and give the dentist more precise expression based on patient anatomy. This technology is unique for a widespread variety of specialties, with a broad range of imaging views for analysis, preparation, case presentation, and cure for the dentist whose practice includes oral surgery, general dentistry, implants, orthodontics and other specialties. We focus on new system which can convert 2-D Dental X-Ray to 3-D Dental X-Ray using the proposed architecture and some needful hardware.

show abstract

Semi-automatic 2D to 3D image conversion using a hybrid Random Walks and graph cuts based approach

Cited by 12 publications

References 12 publications

A framework for estimating relative depth in video

A framework for estimating relative depth in video

Adaptive 2D To 3D Image Conversion Using A Hybrid Graph Cuts And Random Walks Approach

System to Convert 2-D X-Ray Image Into 3-D X-Ray Image in Dentistry

Contact Info

Product

Resources

About