An Approach for Noise Removal on Depth Images


#1

This paper outlines the problem of noise in RGB-D images and proposes a solution that removes much of the noise in almost realtime (32ms for a 752x520 image).

Summary

Their process consists of 3 main phases.

  1. Use edge detector to identify salient edges across the image
  2. Apply jointly bilateral filter to the image to smoothen those regions with concinnous texture values while skip processing the parts with distinct structures
  3. Use the exemplar based scheme to find an optimal patch from those available depth region to the target region

Detailed Explanation of Each Step

Use of Edge Detection Algorithm

  1. Apply available edge detection algorithms such as Canny Edge Detection

Apply jointly bilateral filter

  1. Application of jointly bilateral filter allows us to smooth parts of the image with concinnous texture values while skips processing the parts with distinct structures
  2. Specifically we use the given formula below

– Can’t Display due to 1 image restriction

where p and q represent the center location on image I for the
Gaussian Kernels f and g. kp is the normalizing factor; Ω is
the spatial range

Use of exemplar based scheme

  1. Finds an optimal patch from those available depth
    region to the target region
  2. Adopt the strategy as Criminisi proposed on isophote-driven sampling process

– Can’t display due to 1 image restriction

where the metrics C( p ) and D( p ) are the confidence term and
data term for the priority patch definition P( p ) = C( p )·D( p ).

Results