{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00209377","sets":["1164:3206:10513:10514"]},"path":["10514"],"owner":"44499","recid":"209377","title":["単視点地形景観画像からの3D地形モデルの2段階推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-02-09"},"_buckets":{"deposit":"0d606512-c856-4cfb-b84d-3861cdd711cc"},"_deposit":{"id":"209377","pid":{"type":"depid","value":"209377","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"単視点地形景観画像からの3D地形モデルの2段階推定","author_link":["527585","527584","527587","527586"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"単視点地形景観画像からの3D地形モデルの2段階推定"},{"subitem_title":"Two-step Estimation of 3D Terrain Model from a Single Landscape Image","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"テーマセッション","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-02-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/209377/files/IPSJ-CG21181001.pdf","label":"IPSJ-CG21181001.pdf"},"date":[{"dateType":"Available","dateValue":"2023-02-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CG21181001.pdf","filesize":[{"value":"1.8 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"28"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"17a234b2-fc5e-4c25-88d9-96bd0976ec9a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"高橋, 遼"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"遠藤, 結城"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金森, 由博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"三谷, 純"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10100541","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8949","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"1 枚の景観画像から 3D 地形モデルを復元できれば，その景観を気軽に 3D で鑑賞できる．しかし既存の単視点深度推定手法では，入力画像中の可視領域の深度しか推定できず，復元形状に欠損が生じてしまう．そこで本研究では，1 枚の地形景観画像から，入力画像中の非可視領域も含めた 3D 地形モデルを推定する，CNN による教師あり学習手法を提案する．3D 地形モデルはテクスチャ付き高さマップで表現する．本研究では，入力画像中で推定しやすい可視領域と，推定しづらい非可視領域を分けて扱うため，2 段階の推定を行う．まず，入力画像の 1) 深度と 2) 影や光源の影響がない色情報を CNN で推定し，その結果から三角形メッシュを計算する．そして，三角形メッシュを真上から平行投影して欠損した高さマップとテクスチャを得る．最後に，高さマップとテクスチャの欠損を別の CNN で補完し，3D 地形モデルを得る．以上により，入力画像の遮蔽領域も含めて 3D 地形モデルを推定できる．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータグラフィックスとビジュアル情報学（CG）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-02-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021-CG-181"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":209377,"updated":"2025-01-19T18:31:38.191306+00:00","links":{},"created":"2025-01-19T01:10:41.463857+00:00"}