Robust image reconstruction from multi-view measurements
Gilles Puy, Pierre Vandergheynst

TL;DR
This paper introduces a new method for reconstructing multiple images of a scene from limited multi-view measurements, modeling background and foreground components with geometric transformations and occlusions, and jointly estimating images and transformation parameters.
Contribution
It presents a novel joint reconstruction algorithm that handles geometric transformations and occlusions, with convergence analysis and applications to compressed sensing and super-resolution.
Findings
Algorithm successfully reconstructs images from few measurements.
Convergence to critical points is theoretically established.
Numerical simulations demonstrate effectiveness in super-resolution.
Abstract
We propose a novel method to accurately reconstruct a set of images representing a single scene from few linear multi-view measurements. Each observed image is modeled as the sum of a background image and a foreground one. The background image is common to all observed images but undergoes geometric transformations, as the scene is observed from different viewpoints. In this paper, we assume that these geometric transformations are represented by a few parameters, e.g., translations, rotations, affine transformations, etc.. The foreground images differ from one observed image to another, and are used to model possible occlusions of the scene. The proposed reconstruction algorithm estimates jointly the images and the transformation parameters from the available multi-view measurements. The ideal solution of this multi-view imaging problem minimizes a non-convex functional, and the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSparse and Compressive Sensing Techniques · Medical Imaging Techniques and Applications · Advanced Image Processing Techniques
