Judit Tövissy Automated 3D Image Conversion and Photo Reconstruction on the Web

Analysis of Depth Map Generation for 2D Images Identification of Steps for Reconstruction Innovation: Stencil Filtering Create 3D Website on Phaistos Disk Main Bibliographical References Goals 2

3 This research deals with the new exploitation of already existing information inside an image. No new information is added. Attention

Distance Representation with Depth Maps 4

Depth Map Generation for 2D Images 5

Resulting 3D Conversion 6

Depth Map Generation for 2D Images 7

Resulting 3D Conversion 8

Issue: –Reverse-engineering of an entire dimension is non-trivial. –Reconstruction needs to be based on agreed upon guidelines Assumption #1: –Objects in focus are likely to be closer to the camera than others. Assumption #2: –Objects that are brighter are likely to be in the foreground of an image. Depth Map Generation for 2D Images 9

Steps of Reconstruction 10

Clustering by Mean Shift Algorithm Image Segmentation 11

Qualitative Depth Map (QDM) 12

Previously Developed by MTA SZTAKI Focus Detection 13

Combination of a QDM and a Focus Map Depth-Focus Map 14

Based on the previous Depth-Focus Map Stereoscopic Generation 15

3D Rendering Raytracing Pixel-based 2D Graphics Von Neumann Neighbours Innovation: Stencil Filtering 16 Instead of Von Neumann neighbouring pixels Initiate a Recursive Ray in each direction Find the first non-blank pixel

Recursive Von Neumann Stencil Never documented before Objective: Find relevant pixels Will result in most relevant data Innovation: Stencil Filtering 17

Stencil Filtering Resulting Pixel Filtering Kernel Recursive Von Neumann Neighbouring Pixels Original Pixel 18

Result of an averaging process Clearly visible edges Stencil Filtering – Basic Filtering Kernel 19

Representation of relevance Pixels weighted according to distance Stencil Filtering – Cross Filtering Kernel 20 Bilinear InterpolationCross Filtering

Conclusion: Distance is less relevant than was believed Stencil Filtering – Cross Filtering Kernel 21

Advantage in Realism: Each new pixel is an instance of already existing values in the image Stencil Filtering – Median Filtering Kernel 22

Stereoscopic 3D Conversion 23

24 Ancient Greek artifact near Herakleion The writing remained a mystery for nearly a century TEI of Crete has a solution 3D Website International Collaboration with Dennis Gabor College Phaistos Disk

25 Phaistos Disk

S. Battiato, S. Curti, M. La Cascia, M. Tortora and E. Scordato, "Depth map generation by image classification," Three-Dimensional Image Capture and Applications VI, pp , April 16, L. Kovács and T. Szirányi, "Focus Area Extraction by Blind Deconvolution for Defining Regions of Interest," Pattern Analysis and Machine Intelligence, IEEE Transactions on, pp , June G. Neumann and S. Kopácsi, "Development of 3D Webpages," in CSIT’2013. Proceedings of the 15th international workshop on computer science and information technologies, Vienna-Budapest-Bratislava, S. Battiato, A. Capra, S. Curti and M. La Cascia, Writers, 3d Stereoscopic Image Pairs by Depth-Map Generation. [Performance] Main Bibliographical References 26

Judit Tövissy Automated 3D Image Conversion and Photo Reconstruction on the Web