Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386457107> ?p ?o ?g. }
- W4386457107 endingPage "10001" @default.
- W4386457107 startingPage "10001" @default.
- W4386457107 abstract "Although deep learning-based approaches for video processing have been extensively investigated, the lack of generality in network construction makes it challenging for practical applications, particularly in video restoration. As a result, this paper presents a universal video restoration model that can simultaneously tackle video inpainting and super-resolution tasks. The network, called Video-Restoration-Net (VRN), consists of four components: (1) an encoder to extract features from each frame, (2) a non-local network that recombines features from adjacent frames or different locations of a given frame, (3) a decoder to restore the coarse video from the output of a non-local block, and (4) a refinement network to refine the coarse video on the frame level. The framework is trained in a three-step pipeline to improve training stability for both tasks. Specifically, we first suggest an automated technique to generate full video datasets for super-resolution reconstruction and another complete-incomplete video dataset for inpainting, respectively. A VRN is then trained to inpaint the incomplete videos. Meanwhile, the full video datasets are adopted to train another VRN frame-wisely and validate it against authoritative datasets. We show quantitative comparisons with several baseline models, achieving 40.5042 dB/0.99473 on PSNR/SSIM in the inpainting task, while during the SR task we obtained 28.41 dB/0.7953 and 27.25/0.8152 on BSD100 and Urban100, respectively. The qualitative comparisons demonstrate that our proposed model is able to complete masked regions and implement super-resolution reconstruction in videos of high quality. Furthermore, the above results show that our method has greater versatility both in video inpainting and super-resolution tasks compared to recent models." @default.
- W4386457107 created "2023-09-06" @default.
- W4386457107 creator A5007770072 @default.
- W4386457107 creator A5017096532 @default.
- W4386457107 creator A5043096476 @default.
- W4386457107 date "2023-09-05" @default.
- W4386457107 modified "2023-10-18" @default.
- W4386457107 title "Video-Restoration-Net: Deep Generative Model with Non-Local Network for Inpainting and Super-Resolution Tasks" @default.
- W4386457107 cites W1487937094 @default.
- W4386457107 cites W1763426478 @default.
- W4386457107 cites W1777628566 @default.
- W4386457107 cites W1993120651 @default.
- W4386457107 cites W2044011870 @default.
- W4386457107 cites W2069237980 @default.
- W4386457107 cites W2084689873 @default.
- W4386457107 cites W2109586214 @default.
- W4386457107 cites W2110158442 @default.
- W4386457107 cites W2129873449 @default.
- W4386457107 cites W2210480155 @default.
- W4386457107 cites W2295865687 @default.
- W4386457107 cites W2557227117 @default.
- W4386457107 cites W2557414982 @default.
- W4386457107 cites W2597888278 @default.
- W4386457107 cites W2605737038 @default.
- W4386457107 cites W2738579427 @default.
- W4386457107 cites W2738588019 @default.
- W4386457107 cites W2796286534 @default.
- W4386457107 cites W2866634454 @default.
- W4386457107 cites W2886714066 @default.
- W4386457107 cites W2919046835 @default.
- W4386457107 cites W2962927175 @default.
- W4386457107 cites W2963091558 @default.
- W4386457107 cites W2963270367 @default.
- W4386457107 cites W2963420272 @default.
- W4386457107 cites W2963470893 @default.
- W4386457107 cites W2963729050 @default.
- W4386457107 cites W2964040059 @default.
- W4386457107 cites W2964101377 @default.
- W4386457107 cites W2998075999 @default.
- W4386457107 cites W3035047434 @default.
- W4386457107 cites W3043547428 @default.
- W4386457107 cites W3094825490 @default.
- W4386457107 cites W3096831136 @default.
- W4386457107 cites W3101787898 @default.
- W4386457107 cites W3102015846 @default.
- W4386457107 cites W3108554146 @default.
- W4386457107 cites W3136958399 @default.
- W4386457107 cites W3173210343 @default.
- W4386457107 cites W4240726888 @default.
- W4386457107 cites W54257720 @default.
- W4386457107 doi "https://doi.org/10.3390/app131810001" @default.
- W4386457107 hasPublicationYear "2023" @default.
- W4386457107 type Work @default.
- W4386457107 citedByCount "0" @default.
- W4386457107 crossrefType "journal-article" @default.
- W4386457107 hasAuthorship W4386457107A5007770072 @default.
- W4386457107 hasAuthorship W4386457107A5017096532 @default.
- W4386457107 hasAuthorship W4386457107A5043096476 @default.
- W4386457107 hasBestOaLocation W43864571071 @default.
- W4386457107 hasConcept C111919701 @default.
- W4386457107 hasConcept C115961682 @default.
- W4386457107 hasConcept C11727466 @default.
- W4386457107 hasConcept C118505674 @default.
- W4386457107 hasConcept C126042441 @default.
- W4386457107 hasConcept C154945302 @default.
- W4386457107 hasConcept C162324750 @default.
- W4386457107 hasConcept C187736073 @default.
- W4386457107 hasConcept C2780451532 @default.
- W4386457107 hasConcept C31972630 @default.
- W4386457107 hasConcept C41008148 @default.
- W4386457107 hasConcept C76155785 @default.
- W4386457107 hasConceptScore W4386457107C111919701 @default.
- W4386457107 hasConceptScore W4386457107C115961682 @default.
- W4386457107 hasConceptScore W4386457107C11727466 @default.
- W4386457107 hasConceptScore W4386457107C118505674 @default.
- W4386457107 hasConceptScore W4386457107C126042441 @default.
- W4386457107 hasConceptScore W4386457107C154945302 @default.
- W4386457107 hasConceptScore W4386457107C162324750 @default.
- W4386457107 hasConceptScore W4386457107C187736073 @default.
- W4386457107 hasConceptScore W4386457107C2780451532 @default.
- W4386457107 hasConceptScore W4386457107C31972630 @default.
- W4386457107 hasConceptScore W4386457107C41008148 @default.
- W4386457107 hasConceptScore W4386457107C76155785 @default.
- W4386457107 hasIssue "18" @default.
- W4386457107 hasLocation W43864571071 @default.
- W4386457107 hasOpenAccess W4386457107 @default.
- W4386457107 hasPrimaryLocation W43864571071 @default.
- W4386457107 hasRelatedWork W1574999717 @default.
- W4386457107 hasRelatedWork W166251047 @default.
- W4386457107 hasRelatedWork W2020564930 @default.
- W4386457107 hasRelatedWork W2059339452 @default.
- W4386457107 hasRelatedWork W2068162367 @default.
- W4386457107 hasRelatedWork W2093556634 @default.
- W4386457107 hasRelatedWork W2262668847 @default.
- W4386457107 hasRelatedWork W2370766994 @default.
- W4386457107 hasRelatedWork W2794492057 @default.
- W4386457107 hasRelatedWork W2995115364 @default.
- W4386457107 hasVolume "13" @default.