Generalized Image Acquisition and Analysis

BlurTags: Spatially Varying PSF Estimation with Out-of-Focus Patterns

In this paper, we consider the problem of animation reconstruction, i.e., the reconstruction of shape and motion of a deformable object from dynamic 3D scanner data, without using user provided template models. Unlike pre- vious work that addressed this problem, we do not rely on locally conver- gent optimization but present a system that can handle fast motion, tem- porally disrupted input, and can correctly match objects that disappear for extended time periods in acquisition holes due to occlusion. Our approach is motivated by cartography: We first estimate a few landmark correspon- dences, which are extended to a dense matching and then used to recon- struct geometry and motion. We propose a number of algorithmic building blocks: a scheme for tracking landmarks in temporally coherent and inco- herent data, an algorithm for robust estimation of dense correspondences under topological noise, and the integration of local matching techniques to refine the result. We describe and evaluate the individual components and propose a complete animation reconstruction pipeline based on these ideas. We evaluate our method on a number of standard benchmark data sets and show that we can obtain correct reconstructions in situations where other techniques fail completely or require additional user guidance such as a template model.

Teaching

Computational Optical Imaging

Lecture in winter term 2014/15

Lecturer: Ivo Ihrke

General Information

Course webpage - Libres Savoirs

When: 2014, Sept. 08th to 2014, Oct. 8th
Where: IOA/IOGS buiding room E202
Registration for mailing list: send email to Ivo Ihrke (firstname[dot]lastname[at]inria.fr)

Overview:

This lecture covers advanced digital imaging techniques for image correction and calibration, as well as algorithms and optical considerations for the extraction of three-dimensional content from (sets of) images. We explore the notion of computional-optical codesign and modern high-dimensional imaging techniques.

The tentative course schedule is


Monday 08.09.2014 Introduction and Recapitulation of Image Characteristics [pdf intro & recap]
Wednesday 10.09.2014 High Dynamic Range, Spectral, and Polarization Imaging [pdf hdr/spectral/polarization]
Monday 15.09.2013 Deconvolution [pdf deconvolution]
Wednesday 17.09.2013 Perspective Imaging and the Basics of 3D
Monday 22.09.2013 Structure-from-Motion
Wednesday 24.09.2013 Dense Stereo Techniques and Optical Flow
Monday 29.09.2013 Active 3D Scanning
Wednesday 01.10.2013 Tomography and Volumetric 3D
Monday 06.10.2013 Light Fields
Wednesday 08.10.2014 to be determined - possibly Compressed Sensing

FAQ:


Go back to lecture list



Imprint-Dataprotection