Konferans bildirisi Açık Erişim
Gokay, Dilara; Simsar, Enis; Atici, Efehan; Ahmetoglu, Alper; Yuksel, Atif Emre; Yanardag, Pinar
{ "conceptrecid": "237761", "created": "2022-10-07T10:01:17.143941+00:00", "doi": "10.1109/ICCVW54120.2021.00227", "files": [ { "bucket": "cd4bfb73-46e2-4235-9bc9-c98c1f54569c", "checksum": "md5:355f1be7388c5c96412f21895b0e9ad5", "key": "bib-54bf792e-8fd2-4341-a67a-47097a6dcaf8.txt", "links": { "self": "https://aperta.ulakbim.gov.tr/api/files/cd4bfb73-46e2-4235-9bc9-c98c1f54569c/bib-54bf792e-8fd2-4341-a67a-47097a6dcaf8.txt" }, "size": 226, "type": "txt" } ], "id": 237762, "links": { "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.1109/ICCVW54120.2021.00227.svg", "bucket": "https://aperta.ulakbim.gov.tr/api/files/cd4bfb73-46e2-4235-9bc9-c98c1f54569c", "doi": "https://doi.org/10.1109/ICCVW54120.2021.00227", "html": "https://aperta.ulakbim.gov.tr/record/237762", "latest": "https://aperta.ulakbim.gov.tr/api/records/237762", "latest_html": "https://aperta.ulakbim.gov.tr/record/237762" }, "metadata": { "access_right": "open", "access_right_category": "success", "communities": [ { "id": "tubitak-destekli-proje-yayinlari" } ], "creators": [ { "affiliation": "Tech Univ Munich, Munich, Germany", "name": "Gokay, Dilara" }, { "name": "Simsar, Enis" }, { "affiliation": "Bogazici Univ, Bebek, Turkey", "name": "Atici, Efehan" }, { "affiliation": "Bogazici Univ, Bebek, Turkey", "name": "Ahmetoglu, Alper" }, { "affiliation": "Bogazici Univ, Bebek, Turkey", "name": "Yuksel, Atif Emre" }, { "affiliation": "Bogazici Univ, Bebek, Turkey", "name": "Yanardag, Pinar" } ], "description": "In this paper, we propose a graph-based image-to-image translation framework for generating images. We use rich data collected from the popular creativity platform Artbreeder', where users interpolate multiple GAN-generated images to create artworks. This unique approach of creating new images leads to a tree-like structure where one can track historical data about the creation of a particular image. Inspired by this structure, we propose a novel graph-to-image translation model called Graph2Pix, which takes a graph and corresponding images as input and generates a single image as output. Our experiments show that Graph2Pix is able to outperform several image-to-image translation frameworks on benchmark metrics, including LPIPS (with a 25% improvement) and human perception studies (n = 60), where users preferred the images generated by our method 81.5% of the time.", "doi": "10.1109/ICCVW54120.2021.00227", "has_grant": false, "license": { "id": "cc-by" }, "meeting": { "title": "2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)" }, "publication_date": "2021-01-01", "relations": { "version": [ { "count": 1, "index": 0, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "237762" }, "parent": { "pid_type": "recid", "pid_value": "237761" } } ] }, "resource_type": { "subtype": "conferencepaper", "title": "Konferans bildirisi", "type": "publication" }, "science_branches": [ "Di\u011fer" ], "title": "Graph2Pix: A Graph-Based Image to Image Translation Framework" }, "owners": [ 1 ], "revision": 1, "stats": { "downloads": 5.0, "unique_downloads": 5.0, "unique_views": 18.0, "version_downloads": 5.0, "version_unique_downloads": 5.0, "version_unique_views": 18.0, "version_views": 20.0, "version_volume": 1130.0, "views": 20.0, "volume": 1130.0 }, "updated": "2022-10-07T10:01:17.212078+00:00" }
Görüntülenme | 20 |
İndirme | 5 |
Veri hacmi | 1.1 kB |
Tekil görüntülenme | 18 |
Tekil indirme | 5 |