Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385682017> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4385682017 abstract "Self-supervised video denoising has seen decent progress through the use of blind spot networks. However, under their blind spot constraints, previous self-supervised video denoising methods suffer from significant information loss and texture destruction in either the whole reference frame or neighbor frames, due to their inadequate consideration of the receptive field. Moreover, the limited number of available neighbor frames in previous methods leads to the discarding of distant temporal information. Nonetheless, simply adopting existing recurrent frameworks does not work, since they easily break the constraints on the receptive field imposed by self-supervision. In this paper, we propose RDRF for self-supervised video denoising, which not only fully exploits both the reference and neighbor frames with a denser receptive field, but also better leverages the temporal information from both local and distant neighbor features. First, towards a comprehensive utilization of information from both reference and neighbor frames, RDRF realizes a denser receptive field by taking more neighbor pixels along the spatial and temporal dimensions. Second, it features a self-supervised recurrent video denoising framework, which concurrently integrates distant and near-neighbor temporal features. This enables long-term bidirectional information aggregation, while mitigating error accumulation in the plain recurrent framework. Our method exhibits superior performance on both synthetic and real video denoising datasets. Codes will be available at https://github.com/Wang-XIaoDingdd/RDRF." @default.
- W4385682017 created "2023-08-09" @default.
- W4385682017 creator A5067800206 @default.
- W4385682017 creator A5069785885 @default.
- W4385682017 creator A5072794263 @default.
- W4385682017 creator A5074865219 @default.
- W4385682017 date "2023-08-07" @default.
- W4385682017 modified "2023-10-16" @default.
- W4385682017 title "Recurrent Self-Supervised Video Denoising with Denser Receptive Field" @default.
- W4385682017 doi "https://doi.org/10.48550/arxiv.2308.03608" @default.
- W4385682017 hasPublicationYear "2023" @default.
- W4385682017 type Work @default.
- W4385682017 citedByCount "0" @default.
- W4385682017 crossrefType "posted-content" @default.
- W4385682017 hasAuthorship W4385682017A5067800206 @default.
- W4385682017 hasAuthorship W4385682017A5069785885 @default.
- W4385682017 hasAuthorship W4385682017A5072794263 @default.
- W4385682017 hasAuthorship W4385682017A5074865219 @default.
- W4385682017 hasBestOaLocation W43856820171 @default.
- W4385682017 hasConcept C126042441 @default.
- W4385682017 hasConcept C153180895 @default.
- W4385682017 hasConcept C154945302 @default.
- W4385682017 hasConcept C160633673 @default.
- W4385682017 hasConcept C163294075 @default.
- W4385682017 hasConcept C165696696 @default.
- W4385682017 hasConcept C19071747 @default.
- W4385682017 hasConcept C202444582 @default.
- W4385682017 hasConcept C202474056 @default.
- W4385682017 hasConcept C23431618 @default.
- W4385682017 hasConcept C30814859 @default.
- W4385682017 hasConcept C31972630 @default.
- W4385682017 hasConcept C33923547 @default.
- W4385682017 hasConcept C38652104 @default.
- W4385682017 hasConcept C41008148 @default.
- W4385682017 hasConcept C65483669 @default.
- W4385682017 hasConcept C76155785 @default.
- W4385682017 hasConcept C9652623 @default.
- W4385682017 hasConceptScore W4385682017C126042441 @default.
- W4385682017 hasConceptScore W4385682017C153180895 @default.
- W4385682017 hasConceptScore W4385682017C154945302 @default.
- W4385682017 hasConceptScore W4385682017C160633673 @default.
- W4385682017 hasConceptScore W4385682017C163294075 @default.
- W4385682017 hasConceptScore W4385682017C165696696 @default.
- W4385682017 hasConceptScore W4385682017C19071747 @default.
- W4385682017 hasConceptScore W4385682017C202444582 @default.
- W4385682017 hasConceptScore W4385682017C202474056 @default.
- W4385682017 hasConceptScore W4385682017C23431618 @default.
- W4385682017 hasConceptScore W4385682017C30814859 @default.
- W4385682017 hasConceptScore W4385682017C31972630 @default.
- W4385682017 hasConceptScore W4385682017C33923547 @default.
- W4385682017 hasConceptScore W4385682017C38652104 @default.
- W4385682017 hasConceptScore W4385682017C41008148 @default.
- W4385682017 hasConceptScore W4385682017C65483669 @default.
- W4385682017 hasConceptScore W4385682017C76155785 @default.
- W4385682017 hasConceptScore W4385682017C9652623 @default.
- W4385682017 hasLocation W43856820171 @default.
- W4385682017 hasOpenAccess W4385682017 @default.
- W4385682017 hasPrimaryLocation W43856820171 @default.
- W4385682017 hasRelatedWork W121273120 @default.
- W4385682017 hasRelatedWork W2002009170 @default.
- W4385682017 hasRelatedWork W2034462085 @default.
- W4385682017 hasRelatedWork W2141888456 @default.
- W4385682017 hasRelatedWork W2337415362 @default.
- W4385682017 hasRelatedWork W2483420468 @default.
- W4385682017 hasRelatedWork W2546871836 @default.
- W4385682017 hasRelatedWork W2740820121 @default.
- W4385682017 hasRelatedWork W317572212 @default.
- W4385682017 hasRelatedWork W4312857205 @default.
- W4385682017 isParatext "false" @default.
- W4385682017 isRetracted "false" @default.
- W4385682017 workType "article" @default.