Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202071623> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3202071623 endingPage "2434" @default.
- W3202071623 startingPage "2434" @default.
- W3202071623 abstract "Convolutional neural networks and the per-pixel loss function have shown their potential to be the best combination for super-resolving severely degraded images. However, there are still challenges, such as the massive number of parameters requiring prohibitive memory and vast computing and storage resources as well as time-consuming training and testing. What is more, the per-pixel loss measured by L2 and the Peak Signal-to-Noise Ratio do not correlate well with human perception of image quality, since L2 simply does not capture the intricate characteristics of human visual systems. To address these issues, we propose an effective two-stage hourglass network with multi-task co-optimization, which enables the entire network to focus on training and testing time and inherent image patterns such as local luminance, contrast, structure and data distribution. Moreover, to avoid overwhelming memory overheads, our model is capable of performing real-time single image multi-scale super-resolution, so it is memory-friendly, meaning that memory space is utilized efficiently. In addition, in order to best use the underlying structure and perception of image quality and the intermediate estimates during the inference process, we introduce a cross-scale training strategy with 2×, 3× and 4× image super-resolution. This effective multi-task two-stage network with the cross-scale strategy for multi-scale image super-resolution is named EMTCM. Quantitative and qualitative experiment results show that the proposed EMTCM network outperforms state-of-the-art methods in recovering high-quality images." @default.
- W3202071623 created "2021-10-11" @default.
- W3202071623 creator A5007483551 @default.
- W3202071623 creator A5042444722 @default.
- W3202071623 creator A5052037779 @default.
- W3202071623 creator A5052866574 @default.
- W3202071623 creator A5064335604 @default.
- W3202071623 creator A5083898135 @default.
- W3202071623 date "2021-10-07" @default.
- W3202071623 modified "2023-09-25" @default.
- W3202071623 title "An Effective Multi-Task Two-Stage Network with the Cross-Scale Training Strategy for Multi-Scale Image Super Resolution" @default.
- W3202071623 cites W1885185971 @default.
- W3202071623 cites W1978749115 @default.
- W3202071623 cites W2016482162 @default.
- W3202071623 cites W2133665775 @default.
- W3202071623 cites W2508457857 @default.
- W3202071623 cites W3183394902 @default.
- W3202071623 doi "https://doi.org/10.3390/electronics10192434" @default.
- W3202071623 hasPublicationYear "2021" @default.
- W3202071623 type Work @default.
- W3202071623 sameAs 3202071623 @default.
- W3202071623 citedByCount "2" @default.
- W3202071623 countsByYear W32020716232022 @default.
- W3202071623 crossrefType "journal-article" @default.
- W3202071623 hasAuthorship W3202071623A5007483551 @default.
- W3202071623 hasAuthorship W3202071623A5042444722 @default.
- W3202071623 hasAuthorship W3202071623A5052037779 @default.
- W3202071623 hasAuthorship W3202071623A5052866574 @default.
- W3202071623 hasAuthorship W3202071623A5064335604 @default.
- W3202071623 hasAuthorship W3202071623A5083898135 @default.
- W3202071623 hasBestOaLocation W32020716231 @default.
- W3202071623 hasConcept C111919701 @default.
- W3202071623 hasConcept C115961682 @default.
- W3202071623 hasConcept C121332964 @default.
- W3202071623 hasConcept C154945302 @default.
- W3202071623 hasConcept C160633673 @default.
- W3202071623 hasConcept C162324750 @default.
- W3202071623 hasConcept C187736073 @default.
- W3202071623 hasConcept C2776214188 @default.
- W3202071623 hasConcept C2778755073 @default.
- W3202071623 hasConcept C2780451532 @default.
- W3202071623 hasConcept C31972630 @default.
- W3202071623 hasConcept C41008148 @default.
- W3202071623 hasConcept C55020928 @default.
- W3202071623 hasConcept C62520636 @default.
- W3202071623 hasConcept C81363708 @default.
- W3202071623 hasConcept C98045186 @default.
- W3202071623 hasConceptScore W3202071623C111919701 @default.
- W3202071623 hasConceptScore W3202071623C115961682 @default.
- W3202071623 hasConceptScore W3202071623C121332964 @default.
- W3202071623 hasConceptScore W3202071623C154945302 @default.
- W3202071623 hasConceptScore W3202071623C160633673 @default.
- W3202071623 hasConceptScore W3202071623C162324750 @default.
- W3202071623 hasConceptScore W3202071623C187736073 @default.
- W3202071623 hasConceptScore W3202071623C2776214188 @default.
- W3202071623 hasConceptScore W3202071623C2778755073 @default.
- W3202071623 hasConceptScore W3202071623C2780451532 @default.
- W3202071623 hasConceptScore W3202071623C31972630 @default.
- W3202071623 hasConceptScore W3202071623C41008148 @default.
- W3202071623 hasConceptScore W3202071623C55020928 @default.
- W3202071623 hasConceptScore W3202071623C62520636 @default.
- W3202071623 hasConceptScore W3202071623C81363708 @default.
- W3202071623 hasConceptScore W3202071623C98045186 @default.
- W3202071623 hasIssue "19" @default.
- W3202071623 hasLocation W32020716231 @default.
- W3202071623 hasLocation W32020716232 @default.
- W3202071623 hasOpenAccess W3202071623 @default.
- W3202071623 hasPrimaryLocation W32020716231 @default.
- W3202071623 hasRelatedWork W121273120 @default.
- W3202071623 hasRelatedWork W2002009170 @default.
- W3202071623 hasRelatedWork W2034462085 @default.
- W3202071623 hasRelatedWork W2090093270 @default.
- W3202071623 hasRelatedWork W2337415362 @default.
- W3202071623 hasRelatedWork W2574052219 @default.
- W3202071623 hasRelatedWork W2740820121 @default.
- W3202071623 hasRelatedWork W2963891724 @default.
- W3202071623 hasRelatedWork W317572212 @default.
- W3202071623 hasRelatedWork W4312857205 @default.
- W3202071623 hasVolume "10" @default.
- W3202071623 isParatext "false" @default.
- W3202071623 isRetracted "false" @default.
- W3202071623 magId "3202071623" @default.
- W3202071623 workType "article" @default.