Video filtering and compression by MSU Video Group
- Group Leader: Dr. Dmitriy Vatolin
MSU/YUVsoft Video Filters Available for Companies
We are working with Intel, Samsung, RealNetworks and other companies on adapting our filters other video processing algorithms for specific video streams, applications and hardware like TV-sets, graphics cards, etc. Some of such projects are non-exclusive. Also we have internal researches. Commonly we develop a whole family of some kind of a filter. Generally there are also versions optimized for PC and hardware implementations (ASIC/FPGA/DSP). Please let us know via email@example.com if you are interested in acquiring a license for such filters or making a custom R&D project on video processing, compression, computer vision.
- Auto Segmentation (info
Interest in advanced interactivity with multimedia data significantly increased last years. This cause an advent of new standards proposing the functionality for manipulation with multimedia data (an example of such a standard is MPEG4). That is why segmentation algorithms find its application in wide range of areas including content-based representation of multimedia data, improvement of coding efficiency in video compression standards, sophisticated query and retrieval of video and other content-based functionalities for multimedia applications.
- Advanced FRC (info
FRC (Frame Rate Conversion) algorithms are used in compression, video format conversion, quality enhancement, stereo vision, etc. The most popular application is format conversion. This is the case when FRC is used in order to convert the frame rate of video stream. It is needed for example in order to playback 50Hz video sequence using TV set with 100Hz frame rate.
- Deinterlacer, or i-scan p-scan converter (info
This filter converts interlaced video to progressive. It can be applied to video digitizing, scaling (transcoding), outputing interlaced video to progressive displays (LCD monitors/TV sets, plasma panels, etc). The filter is compared with Smart Deinterlacing included in about 90% of DVD -> DivX converters. Tuning of the filter to achieve industrial-quality conversion was done in a collaboration with Samsung.
- Old Film Restoration (info
The filter is intended to recover video digitized from an old film by removing vertical scratches, noise, tapes defect and other artifacts taking place in old cinema movies.
- Tuner TV Restore filter (info
The filter is intended to recover video captured by a TV Tuner.
- Panorama filter (info
The filter is for contruction of a panorama image of a scene from video which is the only input. Output of the filter is a big picture that contains all scene.
- Video2Photo filter (info
This filter is intended to create still images from videos with higher resolution and better quality than original video. Such an improvement is achieved not only due to intelligent processing of information from one selected frame, but also using neighboring frames.
- SuperResolution filter (info
This filter increases resolution of video sequence improving details and reducing artifacts. It gives significantly better results than typical static upsampling methods because of utilization of useful information from neigboring frames. The algorithm is a way slower than static image upsampling methods, but has significantly lower complexity and better speed than other Super Resolution algorithms known to us.
- SuperPrecision filter (info
The filter is targeted at increasing the colour depth of video (bits per pixel) while preserving details and borders. It is useful for displaying video on high contrast devices like plasma panels. The filter performs reconstruction of image, not just some sort of noise mixing.
- Motion Phase filter (description,
This filter allows to extract and show different phases of some object’s movement simultaneously on each frame. The filter can be useful, for example, for composing of sport teaching films.
- Deshaker filter (description,
This filter is for stabilization of video, or removing of shaking. The feature of our filter is reconstruction of border areas using information from neighboring frames or just previous frames (for 1-pass mode).
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
- MSU Datasets Collection
- Metrics Research
- Video Quality Measurement Tool 3D
- Video Filters
- Other Projects