FIELD: data processing.
SUBSTANCE: invention relates to a method and a device for processing video images for reducing noise. Method of processing video images includes steps of: receiving one sparse channel of a video frame, based on said one sparse channel by means of a neural network, forming a low-resolution parameter map to perform spatial filtering of the video image frame, using the generated parameter map, performing spatial filtering of the video frame for obtaining a processed frame.
EFFECT: reduced complexity of processing video images, high speed and high quality of the processed image.
21 cl, 6 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR REGULARIZING GRADIENTS WHEN TRAINING DEEP NEURAL NETWORK IN ALGORITHM FOR INCREASING FRAME RATE OF VIDEO IMAGE WITH IMAGE DEFORMATION OPERATION AND DEVICE AND MACHINE-READABLE MEDIUM REALIZING SAID METHOD | 2024 |
|
RU2838424C1 |
| RELEVANCY ASSESSMENT FOR ARTIFICIAL NEURAL NETWORKS | 2015 |
|
RU2703343C2 |
| METHOD AND DEVICE OF NOISE FILTERING IN VIDEO SIGNALS | 2008 |
|
RU2364937C1 |
| SYSTEM AND METHOD TO GENERATE AND REPRODUCE 3D VIDEO IMAGE | 2009 |
|
RU2421933C2 |
| METHOD FOR DETECTING EXTENDED LINEAR OBJECTS IN AN IMAGE | 2022 |
|
RU2802991C1 |
| SYSTEM AND METHOD FOR ARTIFICIAL NEURAL NETWORK INVARIANT TO TRANSFERRING | 2017 |
|
RU2656990C1 |
| METHOD FOR SPATIALLY PARAMETERIZED ESTIMATION OF MOTION VECTORS | 2024 |
|
RU2839709C1 |
| CODING SCHEME FOR VIDEO DATA USING DOWN/UP SAMPLING AND NON-LINEAR FILTERING OF DEPTH MAP | 2020 |
|
RU2831969C1 |
| FRAME RATE CONVERSION METHOD SUPPORTING FRAME INTERPOLATION REPLACEMENT WITH MOTION COMPENSATION BY LINEAR FRAME COMBINATION AND DEVICE IMPLEMENTING IT | 2022 |
|
RU2786784C1 |
| METHOD OF DECODING VIDEO FOR MOTION COMPENSATION | 2020 |
|
RU2739499C1 |
