Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 36
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorGunawan, Agusko
dc.contributor.authorKim, Munchurlko
dc.contributor.authorKim, Soo Yeko
dc.contributor.authorLee, Jaehoko
dc.date.accessioned2023-12-06T07:03:29Z-
dc.date.available2023-12-06T07:03:29Z-
dc.date.created2023-11-23-
dc.date.issued2023-06-20-
dc.identifier.citationIEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp.12460 - 12469-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10203/315848-
dc.description.abstractThis paper firstly presents old photo modernization using multiple references by performing stylization and enhancement in a unified manner. In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) framework consisting of a network MROPM-Net and a novel synthetic data generation scheme. MROPM-Net stylizes old photos using multiple references via photorealistic style transfer (PST) and further enhances the results to produce modern-looking images. Meanwhile, the synthetic data generation scheme trains the network to effectively utilize multiple references to perform modernization. To evaluate the performance, we propose a new old photos benchmark dataset (CHD) consisting of diverse natural indoor and outdoor scenes. Extensive experiments show that the proposed method outperforms other baselines in performing modernization on real old photos, even though no old photos were used during training. Moreover, our method can appropriately select styles from multiple references for each semantic region in the old photo to further improve the modernization performance.-
dc.languageEnglish-
dc.publisherThe Computer Vision Foundation-
dc.titleModernizing Old Photos Using Multiple References via Photorealistic Style Transfer-
dc.typeConference-
dc.identifier.wosid001062522104075-
dc.identifier.scopusid2-s2.0-85173919055-
dc.type.rimsCONF-
dc.citation.beginningpage12460-
dc.citation.endingpage12469-
dc.citation.publicationnameIEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023-
dc.identifier.conferencecountryCN-
dc.identifier.conferencelocationVancouver-
dc.identifier.doi10.1109/CVPR52729.2023.01199-
dc.contributor.localauthorKim, Munchurl-
dc.contributor.nonIdAuthorLee, Jaeho-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0