ETD system

Electronic theses and dissertations repository


Tesi etd-11132013-100502

Thesis type
Tesi di dottorato di ricerca
Advancements in multi-view processing for reconstruction, registration and visualization.
Settore scientifico disciplinare
Corso di studi
tutor Dott. Scopigno, Roberto
relatore Dott. Corsini, Massimiliano
Parole chiave
  • Image Processing
  • Computer Vision
  • Computer Graphic
  • Multi-view data
Data inizio appello
Riassunto analitico
The ever-increasing diffusion of digital cameras and the advancements in computer vision, image processing and storage capabilities have lead, in the latest years, to the wide diffusion of digital image collections.<br>A set of digital images is usually referred as a multi-view images set when the pictures cover different views of the same physical object or location.<br><br>In multi-view datasets, correlations between images are exploited in many different ways to increase our capability to gather enhanced understanding and information on a scene.<br>For example, a collection can be enhanced leveraging on the camera position and orientation, or with information about the 3D structure of the scene.<br>The range of applications of multi-view data is really wide, encompassing diverse fields such as image-based reconstruction, image-based localization, navigation of virtual environments, collective photographic retouching, computational photography, object recognition, etc.<br>For all these reasons, the development of new algorithms to effectively create, process, and visualize this type of data is an active research trend.<br><br>The thesis will present four different advancements related to different aspects of the multi-view data processing:<br><br>- Image-based 3D reconstruction: we present a pre-processing algorithm, that is a special color-to-gray conversion. This was developed with the aim to improve the accuracy of image-based reconstruction algorithms.<br>In particular, we show how different dense stereo matching results can be enhanced by application of a domain separation approach that pre-computes a single optimized numerical value for each image location.<br><br>- Image-based appearance reconstruction: we present a multi-view processing algorithm, this can enhance the quality of the color transfer from multi-view images to a geo-referenced 3D model of a location of interest.<br>The proposed approach computes virtual shadows and allows to automatically segment shadowed regions from the input images preventing to use those pixels in subsequent texture synthesis.<br><br>- 2D to 3D registration: we present an unsupervised localization and registration system. This system can recognize a site that has been framed in a multi-view data and calibrate it on a pre-existing 3D representation.<br>The system has a very high accuracy and it can validate the result in a completely unsupervised manner.<br>The system accuracy is enough to seamlessly view input images correctly super-imposed on the 3D location of interest.<br><br>- Visualization: we present PhotoCloud, a real-time client-server system for interactive exploration of high resolution 3D models and up to several thousand photographs aligned over this 3D data.<br>PhotoCloud supports any 3D models that can be rendered in a depth-coherent way and arbitrary multi-view image collections.<br>Moreover, it tolerates 2D-to-2D and 2D-to-3D misalignments, and it provides scalable visualization of generic integrated 2D and 3D datasets by exploiting data duality.<br>A set of effective 3D navigation controls, tightly integrated with innovative thumbnail bars, enhances the user navigation.<br><br>These advancements have been developed in tourism and cultural heritage application contexts, but they are not limited to these.