Electrical Engineering-Systems Dept.

*** SEMINAR ***

Yaron Eshet

(M.Sc. student under the supervision of Dr. Shai Avidan)

on the subject:

Patches in 3D Space

We extend patch based methods to work on patches in 3D space. This improvement is then translated to improved image denoising. We start with Coherency Sensitive Hashing (CSH), which is an algorithm for matching patches between two RGB images, and extend it to work with RGBD images. This is done by warping all 3D patches to a common virtual plane in which CSH is performed. This works well but introduces warping errors for patches with a normal or depth that are very different from those of the virtual plane. To address this, we estimate the dominant 3D planes in the scene and compute CSH on each plane in parallel, before merging the matching results. The process of finding for each image patch a large set of candidate matches is accelerated using a social amplification step. Experiments demonstrate the clear advantage of using 3D patches both for patch matching and image denoising.