Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327732016> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4327732016 abstract "The demands of high-quality videos captured by camera become bigger due to the rapid development of pattern recognition and artificial intelligence. Video denoising is the key technology to obtain clear videos. However, the research on video denoising is far from enough now. In this paper, we propose a video denoising method based on convolutional neural network architecture to reduce the noise from the sensor system. We improve the loss function of noise estimation by imposing adaptive penalty on under-estimation error of noise level which makes our method perform robustly. Furthermore, we make use of multi-level features to guide the spatial denoising, where multilayer semantic information of the image is regarded as the perceptual loss. Instead of relying on Optical Flow solving the characterization of inter-frame information, we utilize U-Net-like structure to handle motion implicitly. It is less computationally expensive and avoids distortions caused by inaccurate flow and object occlusion. In order to locate temporal features and suppress useless information, the attention mechanism is introduced to the skip connections of the U-Net-like structure. Experimental results demonstrate that the proposed algorithm outputs more convincing results in both peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) indexes when processing Gaussian noise, synthetic real noise, and real noise compared with selected approaches." @default.
- W4327732016 created "2023-03-18" @default.
- W4327732016 creator A5037663621 @default.
- W4327732016 creator A5050982728 @default.
- W4327732016 creator A5076699095 @default.
- W4327732016 date "2023-04-22" @default.
- W4327732016 modified "2023-09-23" @default.
- W4327732016 title "Spatio-Temporal Video Denoising Based on Attention Mechanism" @default.
- W4327732016 cites W1965221572 @default.
- W4327732016 cites W2056370875 @default.
- W4327732016 cites W2508457857 @default.
- W4327732016 cites W2556068545 @default.
- W4327732016 cites W2943852415 @default.
- W4327732016 cites W2984728496 @default.
- W4327732016 cites W2999838674 @default.
- W4327732016 cites W3000255543 @default.
- W4327732016 cites W3024754576 @default.
- W4327732016 cites W3082170314 @default.
- W4327732016 cites W3104725225 @default.
- W4327732016 doi "https://doi.org/10.1142/s0218001423550066" @default.
- W4327732016 hasPublicationYear "2023" @default.
- W4327732016 type Work @default.
- W4327732016 citedByCount "0" @default.
- W4327732016 crossrefType "journal-article" @default.
- W4327732016 hasAuthorship W4327732016A5037663621 @default.
- W4327732016 hasAuthorship W4327732016A5050982728 @default.
- W4327732016 hasAuthorship W4327732016A5076699095 @default.
- W4327732016 hasConcept C115961682 @default.
- W4327732016 hasConcept C126042441 @default.
- W4327732016 hasConcept C153180895 @default.
- W4327732016 hasConcept C154945302 @default.
- W4327732016 hasConcept C155542232 @default.
- W4327732016 hasConcept C163294075 @default.
- W4327732016 hasConcept C202474056 @default.
- W4327732016 hasConcept C23431618 @default.
- W4327732016 hasConcept C2781238097 @default.
- W4327732016 hasConcept C30814859 @default.
- W4327732016 hasConcept C31972630 @default.
- W4327732016 hasConcept C41008148 @default.
- W4327732016 hasConcept C4199805 @default.
- W4327732016 hasConcept C76155785 @default.
- W4327732016 hasConcept C99498987 @default.
- W4327732016 hasConceptScore W4327732016C115961682 @default.
- W4327732016 hasConceptScore W4327732016C126042441 @default.
- W4327732016 hasConceptScore W4327732016C153180895 @default.
- W4327732016 hasConceptScore W4327732016C154945302 @default.
- W4327732016 hasConceptScore W4327732016C155542232 @default.
- W4327732016 hasConceptScore W4327732016C163294075 @default.
- W4327732016 hasConceptScore W4327732016C202474056 @default.
- W4327732016 hasConceptScore W4327732016C23431618 @default.
- W4327732016 hasConceptScore W4327732016C2781238097 @default.
- W4327732016 hasConceptScore W4327732016C30814859 @default.
- W4327732016 hasConceptScore W4327732016C31972630 @default.
- W4327732016 hasConceptScore W4327732016C41008148 @default.
- W4327732016 hasConceptScore W4327732016C4199805 @default.
- W4327732016 hasConceptScore W4327732016C76155785 @default.
- W4327732016 hasConceptScore W4327732016C99498987 @default.
- W4327732016 hasFunder F4320321001 @default.
- W4327732016 hasFunder F4320323086 @default.
- W4327732016 hasFunder F4320335787 @default.
- W4327732016 hasIssue "06" @default.
- W4327732016 hasLocation W43277320161 @default.
- W4327732016 hasOpenAccess W4327732016 @default.
- W4327732016 hasPrimaryLocation W43277320161 @default.
- W4327732016 hasRelatedWork W1981274447 @default.
- W4327732016 hasRelatedWork W2081458845 @default.
- W4327732016 hasRelatedWork W2128319034 @default.
- W4327732016 hasRelatedWork W2244560705 @default.
- W4327732016 hasRelatedWork W2330524259 @default.
- W4327732016 hasRelatedWork W2534746541 @default.
- W4327732016 hasRelatedWork W2783980107 @default.
- W4327732016 hasRelatedWork W2965570359 @default.
- W4327732016 hasRelatedWork W3034499084 @default.
- W4327732016 hasRelatedWork W3084370450 @default.
- W4327732016 hasVolume "37" @default.
- W4327732016 isParatext "false" @default.
- W4327732016 isRetracted "false" @default.
- W4327732016 workType "article" @default.