Photoshop MSU Image Restoration
- Project, ideas: Dmitriy Vatolin, Dmitriy Kulikov, Maxim Makhinya
- Implementation: Keira Ragulina
The plug-in for image processing program Adobe Photoshop CS2. Other versions of Photoshop are not checked.
The filter filling in picked out damaged area using only space data. This filter is intended to repairing image (removing scratches, spots and etc), removing undesirable “objects”.
History of versions:
- 1.5 - add two image restoration algorithms, speed up filter and reduce number of parameters
- 0.9b - first beta version
Settings

Algorithm - used algorithm
Block radius - block radius for compare.
Choose this radius equal to typical element of damaged area.
Plug-in works longer with the greater block radius.
1 <= Block radius <= 10
Search radius - radius of similar block search area.
Choose this radius equal to area radius similar to the damaged area.
Plug-in works longer with the greater search radius.
Block radius + 2 <= Search radius <= 30
For Fast algorithm:
Block radius + Bondary zone radius + 2 <= Search radius <= 30
Bondary zone radius = (2 * Block radius + 1) / 6
Examples
High quality algorithm

Source image

Mask using for image restoration

Restored image
Normal algorithm

Source image

Mask using for image restoration

Restored image
Fast algorithm

Source image

Mask using for image restoration

Restored image
Download
- Open this file Photoshop CS2. Unpacked in the folder “Plug-Ins”.
Plug-in should appear in menu
Filter -> MSU Graphics & Media Lab (at the very bottom). File size 60 KB (in ZIP) - Program license for non-commercial usage
For common questions about filter’s work and other issues about it please contact us.
E-mail: video@graphics.cs.msu.ru
-
MSU Benchmark Collection
- MSU Video Upscalers Benchmark 2022
- MSU Video Deblurring Benchmark 2022
- MSU Video Frame Interpolation Benchmark 2022
- MSU HDR Video Reconstruction Benchmark 2022
- MSU Super-Resolution for Video Compression Benchmark 2022
- MSU No-Reference Video Quality Metrics Benchmark 2022
- MSU Full-Reference Video Quality Metrics Benchmark 2022
- MSU Video Alignment and Retrieval Benchmark
- MSU Mobile Video Codecs Benchmark 2021
- MSU Video Super-Resolution Benchmark
- MSU Shot Boundary Detection Benchmark 2020
- MSU Deinterlacer Benchmark
- The VideoMatting Project
- Video Completion
- Codecs Comparisons & Optimization
- VQMT
- MSU Datasets Collection
- Metrics Research
- Video Quality Measurement Tool 3D
- Video Filters
- Other Projects