Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200326209> ?p ?o ?g. }
- W4200326209 endingPage "13" @default.
- W4200326209 startingPage "1" @default.
- W4200326209 abstract "While self-attention has been successfully applied in a variety of natural language processing and computer vision tasks, its application in Monte Carlo (MC) image denoising has not yet been well explored. This paper presents a self-attention based MC denoising deep learning network based on the fact that self-attention is essentially non-local means filtering in the embedding space which makes it inherently very suitable for the denoising task. Particularly, we modify the standard self-attention mechanism to an auxiliary feature guided self-attention that considers the by-products (e.g., auxiliary feature buffers) of the MC rendering process. As a critical prerequisite to fully exploit the performance of self-attention, we design a multi-scale feature extraction stage, which provides a rich set of raw features for the later self-attention module. As self-attention poses a high computational complexity, we describe several ways that accelerate it. Ablation experiments validate the necessity and effectiveness of the above design choices. Comparison experiments show that the proposed self-attention based MC denoising method outperforms the current state-of-the-art methods." @default.
- W4200326209 created "2021-12-31" @default.
- W4200326209 creator A5025851882 @default.
- W4200326209 creator A5027540915 @default.
- W4200326209 creator A5031765917 @default.
- W4200326209 creator A5067363489 @default.
- W4200326209 creator A5068461686 @default.
- W4200326209 creator A5083221103 @default.
- W4200326209 date "2021-12-01" @default.
- W4200326209 modified "2023-10-14" @default.
- W4200326209 title "Monte Carlo denoising via auxiliary feature guided self-attention" @default.
- W4200326209 cites W1974524841 @default.
- W4200326209 cites W1977778188 @default.
- W4200326209 cites W1979011254 @default.
- W4200326209 cites W1984696318 @default.
- W4200326209 cites W2020681231 @default.
- W4200326209 cites W2036532817 @default.
- W4200326209 cites W2077323204 @default.
- W4200326209 cites W2097073572 @default.
- W4200326209 cites W2097117768 @default.
- W4200326209 cites W2125561951 @default.
- W4200326209 cites W2135359136 @default.
- W4200326209 cites W2207744012 @default.
- W4200326209 cites W2466064361 @default.
- W4200326209 cites W2737368828 @default.
- W4200326209 cites W2738449271 @default.
- W4200326209 cites W2811168853 @default.
- W4200326209 cites W2903914407 @default.
- W4200326209 cites W2944270038 @default.
- W4200326209 cites W2944820846 @default.
- W4200326209 cites W2958080091 @default.
- W4200326209 cites W2963091558 @default.
- W4200326209 cites W2964046397 @default.
- W4200326209 cites W2971100256 @default.
- W4200326209 cites W2972600666 @default.
- W4200326209 cites W3006224067 @default.
- W4200326209 cites W3014685569 @default.
- W4200326209 cites W3034655362 @default.
- W4200326209 cites W3034779438 @default.
- W4200326209 cites W3035022492 @default.
- W4200326209 cites W3109789611 @default.
- W4200326209 cites W3110029631 @default.
- W4200326209 cites W3134812768 @default.
- W4200326209 cites W3142122793 @default.
- W4200326209 cites W3179869055 @default.
- W4200326209 cites W3183677218 @default.
- W4200326209 cites W4242198876 @default.
- W4200326209 cites W4244324388 @default.
- W4200326209 cites W4229958016 @default.
- W4200326209 doi "https://doi.org/10.1145/3478513.3480565" @default.
- W4200326209 hasPublicationYear "2021" @default.
- W4200326209 type Work @default.
- W4200326209 citedByCount "11" @default.
- W4200326209 countsByYear W42003262092022 @default.
- W4200326209 countsByYear W42003262092023 @default.
- W4200326209 crossrefType "journal-article" @default.
- W4200326209 hasAuthorship W4200326209A5025851882 @default.
- W4200326209 hasAuthorship W4200326209A5027540915 @default.
- W4200326209 hasAuthorship W4200326209A5031765917 @default.
- W4200326209 hasAuthorship W4200326209A5067363489 @default.
- W4200326209 hasAuthorship W4200326209A5068461686 @default.
- W4200326209 hasAuthorship W4200326209A5083221103 @default.
- W4200326209 hasConcept C105795698 @default.
- W4200326209 hasConcept C119857082 @default.
- W4200326209 hasConcept C138885662 @default.
- W4200326209 hasConcept C154945302 @default.
- W4200326209 hasConcept C163294075 @default.
- W4200326209 hasConcept C165696696 @default.
- W4200326209 hasConcept C19499675 @default.
- W4200326209 hasConcept C205711294 @default.
- W4200326209 hasConcept C2776401178 @default.
- W4200326209 hasConcept C33923547 @default.
- W4200326209 hasConcept C38652104 @default.
- W4200326209 hasConcept C41008148 @default.
- W4200326209 hasConcept C41608201 @default.
- W4200326209 hasConcept C41895202 @default.
- W4200326209 hasConceptScore W4200326209C105795698 @default.
- W4200326209 hasConceptScore W4200326209C119857082 @default.
- W4200326209 hasConceptScore W4200326209C138885662 @default.
- W4200326209 hasConceptScore W4200326209C154945302 @default.
- W4200326209 hasConceptScore W4200326209C163294075 @default.
- W4200326209 hasConceptScore W4200326209C165696696 @default.
- W4200326209 hasConceptScore W4200326209C19499675 @default.
- W4200326209 hasConceptScore W4200326209C205711294 @default.
- W4200326209 hasConceptScore W4200326209C2776401178 @default.
- W4200326209 hasConceptScore W4200326209C33923547 @default.
- W4200326209 hasConceptScore W4200326209C38652104 @default.
- W4200326209 hasConceptScore W4200326209C41008148 @default.
- W4200326209 hasConceptScore W4200326209C41608201 @default.
- W4200326209 hasConceptScore W4200326209C41895202 @default.
- W4200326209 hasFunder F4320321001 @default.
- W4200326209 hasFunder F4320321921 @default.
- W4200326209 hasFunder F4320335787 @default.
- W4200326209 hasIssue "6" @default.
- W4200326209 hasLocation W42003262091 @default.
- W4200326209 hasOpenAccess W4200326209 @default.
- W4200326209 hasPrimaryLocation W42003262091 @default.
- W4200326209 hasRelatedWork W1607315280 @default.