The patch transform
Related Experiment Video
Updated: Jan 6, 2026

The Use of the Patch-Clamp Technique to Study the Thermogenic Capacity of Mitochondria
Published on: May 3, 2021
Taeg Sang Cho1, Shai Avidan, William T Freeman
1CSAIL, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. taegsang@mit.edu
Abstract:
The patch transform represents an image as a bag of overlapping patches sampled on a regular grid. This representation allows users to manipulate images in the patch domain, which then seeds the inverse patch transform to synthesize modified images. Possible modifications include the spatial locations of patches, the size of the output image, or the pool of patches from which an image is reconstructed. When no modifications are made, the inverse patch transform reduces to solving a jigsaw puzzle. The inverse patch transform is posed as a patch assignment problem on a Markov random field (MRF), where each patch should be used only once and neighboring patches should fit to form a plausible image. We find an approximate solution to the MRF using loopy belief propagation, introducing an approximation that encourages the solution to use each patch only once. The image reconstruction algorithm scales well with the total number of patches through label pruning. In addition, structural misalignment artifacts are suppressed through a patch jittering scheme that spatially jitters the assigned patches. We demonstrate the patch transform and its effectiveness on natural images.
Related Concept Videos
Transformations of Functions I
Transformations of Functions II
Transformations of Functions III
Transformation
Source Transformation
It is essential to note that when...
Bacterial Transformation
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...

