Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076009> ?p ?o ?g. }
- W4386076009 abstract "Unpaired image-to-image translation aims to learn proper mappings that can map images from one domain to another domain while preserving the content of the input image. However, with large enough capacities, the network can learn to map the inputs to any random permutation of images in another domain. Existing methods treat two domains as discrete and propose different assumptions to address this problem. In this paper, we start from a different perspective and consider the paths connecting the two domains. We assume that the optimal path length between the input and output image should be the shortest among all possible paths. Based on this assumption, we propose a new method to allow generating images along the path and present a simple way to encourage the network to find the shortest path without pair information. Extensive experiments on various tasks demonstrate the superiority of our approach. The code is available at https://github.com/Mid-Push/santa." @default.
- W4386076009 created "2023-08-23" @default.
- W4386076009 creator A5010906829 @default.
- W4386076009 creator A5016038041 @default.
- W4386076009 creator A5065203711 @default.
- W4386076009 creator A5091227928 @default.
- W4386076009 date "2023-06-01" @default.
- W4386076009 modified "2023-10-15" @default.
- W4386076009 title "Unpaired Image-to-Image Translation with Shortest Path Regularization" @default.
- W4386076009 cites W2112494174 @default.
- W4386076009 cites W2340897893 @default.
- W4386076009 cites W2474265885 @default.
- W4386076009 cites W2592232824 @default.
- W4386076009 cites W2593414223 @default.
- W4386076009 cites W2603777577 @default.
- W4386076009 cites W2943322963 @default.
- W4386076009 cites W2953421261 @default.
- W4386076009 cites W2962793481 @default.
- W4386076009 cites W2962850830 @default.
- W4386076009 cites W2962903125 @default.
- W4386076009 cites W2963073614 @default.
- W4386076009 cites W2963403405 @default.
- W4386076009 cites W2963444790 @default.
- W4386076009 cites W2963767194 @default.
- W4386076009 cites W2963789515 @default.
- W4386076009 cites W2964231450 @default.
- W4386076009 cites W2989855043 @default.
- W4386076009 cites W3034600949 @default.
- W4386076009 cites W3035190116 @default.
- W4386076009 cites W3035398999 @default.
- W4386076009 cites W3035480894 @default.
- W4386076009 cites W3105747145 @default.
- W4386076009 cites W3106941582 @default.
- W4386076009 cites W3167101089 @default.
- W4386076009 cites W3168347507 @default.
- W4386076009 cites W3173268697 @default.
- W4386076009 cites W3173372951 @default.
- W4386076009 cites W3174004012 @default.
- W4386076009 cites W3193057479 @default.
- W4386076009 cites W3201741124 @default.
- W4386076009 cites W3202433296 @default.
- W4386076009 cites W3203398299 @default.
- W4386076009 cites W4221159622 @default.
- W4386076009 cites W4312696983 @default.
- W4386076009 cites W4312709987 @default.
- W4386076009 cites W4312787185 @default.
- W4386076009 cites W4313178739 @default.
- W4386076009 doi "https://doi.org/10.1109/cvpr52729.2023.00981" @default.
- W4386076009 hasPublicationYear "2023" @default.
- W4386076009 type Work @default.
- W4386076009 citedByCount "0" @default.
- W4386076009 crossrefType "proceedings-article" @default.
- W4386076009 hasAuthorship W4386076009A5010906829 @default.
- W4386076009 hasAuthorship W4386076009A5016038041 @default.
- W4386076009 hasAuthorship W4386076009A5065203711 @default.
- W4386076009 hasAuthorship W4386076009A5091227928 @default.
- W4386076009 hasConcept C104317684 @default.
- W4386076009 hasConcept C105580179 @default.
- W4386076009 hasConcept C11413529 @default.
- W4386076009 hasConcept C115961682 @default.
- W4386076009 hasConcept C121332964 @default.
- W4386076009 hasConcept C12713177 @default.
- W4386076009 hasConcept C132525143 @default.
- W4386076009 hasConcept C134306372 @default.
- W4386076009 hasConcept C149364088 @default.
- W4386076009 hasConcept C154945302 @default.
- W4386076009 hasConcept C177264268 @default.
- W4386076009 hasConcept C185592680 @default.
- W4386076009 hasConcept C199360897 @default.
- W4386076009 hasConcept C21308566 @default.
- W4386076009 hasConcept C22590252 @default.
- W4386076009 hasConcept C24890656 @default.
- W4386076009 hasConcept C2776135515 @default.
- W4386076009 hasConcept C2776760102 @default.
- W4386076009 hasConcept C2777735758 @default.
- W4386076009 hasConcept C2779757391 @default.
- W4386076009 hasConcept C31972630 @default.
- W4386076009 hasConcept C33923547 @default.
- W4386076009 hasConcept C36503486 @default.
- W4386076009 hasConcept C41008148 @default.
- W4386076009 hasConcept C55493867 @default.
- W4386076009 hasConcept C80444323 @default.
- W4386076009 hasConceptScore W4386076009C104317684 @default.
- W4386076009 hasConceptScore W4386076009C105580179 @default.
- W4386076009 hasConceptScore W4386076009C11413529 @default.
- W4386076009 hasConceptScore W4386076009C115961682 @default.
- W4386076009 hasConceptScore W4386076009C121332964 @default.
- W4386076009 hasConceptScore W4386076009C12713177 @default.
- W4386076009 hasConceptScore W4386076009C132525143 @default.
- W4386076009 hasConceptScore W4386076009C134306372 @default.
- W4386076009 hasConceptScore W4386076009C149364088 @default.
- W4386076009 hasConceptScore W4386076009C154945302 @default.
- W4386076009 hasConceptScore W4386076009C177264268 @default.
- W4386076009 hasConceptScore W4386076009C185592680 @default.
- W4386076009 hasConceptScore W4386076009C199360897 @default.
- W4386076009 hasConceptScore W4386076009C21308566 @default.
- W4386076009 hasConceptScore W4386076009C22590252 @default.
- W4386076009 hasConceptScore W4386076009C24890656 @default.
- W4386076009 hasConceptScore W4386076009C2776135515 @default.
- W4386076009 hasConceptScore W4386076009C2776760102 @default.