Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311832596> ?p ?o ?g. }
- W4311832596 abstract "This paper proposes an iterative score-based generative model for solving the automatic colorization problem. Although unsupervised learning methods have shown the capability to generate plausible color, inadequate exploration of detailed information and data dimensions still limit the performance of the colorization model. Considering that the number of samples in score-based generative model has influence on estimating the target gradients and the gradient map possesses important latent information of the image, the inference process of the generative modeling is conducted in joint intensity–gradient domain for colorization. Specifically, a set of intensity–gradient formed high-dimensional tensors are trained, via the score matching, to attain the gradient of data distribution in joint intensity–gradient domain. As the score function is determined, data samples are generated by means of annealed Langevin dynamics, forming an iterative colorization procedure. Furthermore, the joint intensity–gradient constraint in data-fidelity term is proposed to limit the degree of freedom within generative model at the iterative colorization stage, thus being conducive to edge-preserving colorization effect. Experimental results conveyed the remarkable performance and diversity of our proposed method." @default.
- W4311832596 created "2022-12-31" @default.
- W4311832596 creator A5004908854 @default.
- W4311832596 creator A5026432478 @default.
- W4311832596 creator A5029636776 @default.
- W4311832596 creator A5033970680 @default.
- W4311832596 creator A5069856050 @default.
- W4311832596 creator A5075249619 @default.
- W4311832596 date "2022-12-17" @default.
- W4311832596 modified "2023-10-15" @default.
- W4311832596 title "Joint intensity–gradient guided generative modeling for colorization" @default.
- W4311832596 cites W1012977646 @default.
- W4311832596 cites W1471960936 @default.
- W4311832596 cites W1694135408 @default.
- W4311832596 cites W1912194039 @default.
- W4311832596 cites W1976499485 @default.
- W4311832596 cites W2013035813 @default.
- W4311832596 cites W2017514550 @default.
- W4311832596 cites W2085020374 @default.
- W4311832596 cites W2117539524 @default.
- W4311832596 cites W2120963736 @default.
- W4311832596 cites W2132504201 @default.
- W4311832596 cites W2136154655 @default.
- W4311832596 cites W2169321544 @default.
- W4311832596 cites W2170163526 @default.
- W4311832596 cites W2294092488 @default.
- W4311832596 cites W2295537950 @default.
- W4311832596 cites W2308529009 @default.
- W4311832596 cites W2326925005 @default.
- W4311832596 cites W2331376995 @default.
- W4311832596 cites W2461158874 @default.
- W4311832596 cites W2493917951 @default.
- W4311832596 cites W2561196672 @default.
- W4311832596 cites W2584268138 @default.
- W4311832596 cites W2584890299 @default.
- W4311832596 cites W2590274298 @default.
- W4311832596 cites W2615988339 @default.
- W4311832596 cites W2776881395 @default.
- W4311832596 cites W2801197735 @default.
- W4311832596 cites W2885673693 @default.
- W4311832596 cites W2888796286 @default.
- W4311832596 cites W2891401260 @default.
- W4311832596 cites W2903874033 @default.
- W4311832596 cites W2941137837 @default.
- W4311832596 cites W2957365494 @default.
- W4311832596 cites W2963008638 @default.
- W4311832596 cites W2963073614 @default.
- W4311832596 cites W2963181089 @default.
- W4311832596 cites W2963502052 @default.
- W4311832596 cites W2963805028 @default.
- W4311832596 cites W2969785455 @default.
- W4311832596 cites W2997095758 @default.
- W4311832596 cites W3000407986 @default.
- W4311832596 cites W3010626953 @default.
- W4311832596 cites W3034583007 @default.
- W4311832596 cites W3034832575 @default.
- W4311832596 cites W3034838697 @default.
- W4311832596 cites W3101436106 @default.
- W4311832596 doi "https://doi.org/10.1007/s00371-022-02747-0" @default.
- W4311832596 hasPublicationYear "2022" @default.
- W4311832596 type Work @default.
- W4311832596 citedByCount "1" @default.
- W4311832596 countsByYear W43118325962023 @default.
- W4311832596 crossrefType "journal-article" @default.
- W4311832596 hasAuthorship W4311832596A5004908854 @default.
- W4311832596 hasAuthorship W4311832596A5026432478 @default.
- W4311832596 hasAuthorship W4311832596A5029636776 @default.
- W4311832596 hasAuthorship W4311832596A5033970680 @default.
- W4311832596 hasAuthorship W4311832596A5069856050 @default.
- W4311832596 hasAuthorship W4311832596A5075249619 @default.
- W4311832596 hasBestOaLocation W43118325962 @default.
- W4311832596 hasConcept C11413529 @default.
- W4311832596 hasConcept C127413603 @default.
- W4311832596 hasConcept C153180895 @default.
- W4311832596 hasConcept C153258448 @default.
- W4311832596 hasConcept C154945302 @default.
- W4311832596 hasConcept C159694833 @default.
- W4311832596 hasConcept C167966045 @default.
- W4311832596 hasConcept C170154142 @default.
- W4311832596 hasConcept C18555067 @default.
- W4311832596 hasConcept C2524010 @default.
- W4311832596 hasConcept C2776036281 @default.
- W4311832596 hasConcept C33923547 @default.
- W4311832596 hasConcept C39890363 @default.
- W4311832596 hasConcept C41008148 @default.
- W4311832596 hasConcept C50644808 @default.
- W4311832596 hasConceptScore W4311832596C11413529 @default.
- W4311832596 hasConceptScore W4311832596C127413603 @default.
- W4311832596 hasConceptScore W4311832596C153180895 @default.
- W4311832596 hasConceptScore W4311832596C153258448 @default.
- W4311832596 hasConceptScore W4311832596C154945302 @default.
- W4311832596 hasConceptScore W4311832596C159694833 @default.
- W4311832596 hasConceptScore W4311832596C167966045 @default.
- W4311832596 hasConceptScore W4311832596C170154142 @default.
- W4311832596 hasConceptScore W4311832596C18555067 @default.
- W4311832596 hasConceptScore W4311832596C2524010 @default.
- W4311832596 hasConceptScore W4311832596C2776036281 @default.
- W4311832596 hasConceptScore W4311832596C33923547 @default.
- W4311832596 hasConceptScore W4311832596C39890363 @default.
- W4311832596 hasConceptScore W4311832596C41008148 @default.