Real-time free viewpoint rendering via viewport range driven polygon plane arrangement

• Item type: SIG Technical Reports(1)
• 公開日: 2019-06-06
• タイトル: Real-time free viewpoint rendering via viewport range driven polygon plane arrangement
• タイトル / 言語: en
• タイトル: Real-time free viewpoint rendering via viewport range driven polygon plane arrangement
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: AVM研究会最優秀賞受賞記念講演
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: KDDI Research, Inc.
• 著者所属: KDDI Research, Inc.
• 著者所属: KDDI Research, Inc.
• 著者所属: KDDI Research, Inc.
• 著者所属(英): en
• 著者所属(英): KDDI Research, Inc.
• 著者所属(英): en
• 著者所属(英): KDDI Research, Inc.
• 著者所属(英): en
• 著者所属(英): KDDI Research, Inc.
• 著者所属(英): en
• 著者所属(英): KDDI Research, Inc.
• 著者名: Keisuke, Nonaka; Ryosuke, Watanabe; Jun, Chen; Sei, Naito
• 著者名(英): Keisuke, Nonaka; Ryosuke, Watanabe; Jun, Chen; Sei, Naito
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Free viewpoint technologies that synthesize virtual viewpoint by using multiple actual videos would provide immersive experiences for users. To realize this concept, many conventional methods have been proposed. However, these methods require high computational cost to synthesize a virtual viewpoint because they have to calculate huge data to express three-dimensional information. To overcome this problem, we propose a simple and fast free viewpoint synthesis method based on a visual hull, which is a general concept in this field. We calculate the silhouette of an object along view-dependent planes in virtual space by simple projection from images to the 3D space, and express the whole shape of the object by integrating the planes. This scheme works very quickly while providing fine quality because it consists of standard functions in general GPU architecture. The experimental results show our method can generate a fine virtual view of an object by using multiple videos in real time.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Free viewpoint technologies that synthesize virtual viewpoint by using multiple actual videos would provide immersive experiences for users. To realize this concept, many conventional methods have been proposed. However, these methods require high computational cost to synthesize a virtual viewpoint because they have to calculate huge data to express three-dimensional information. To overcome this problem, we propose a simple and fast free viewpoint synthesis method based on a visual hull, which is a general concept in this field. We calculate the silhouette of an object along view-dependent planes in virtual space by simple projection from images to the 3D space, and express the whole shape of the object by integrating the planes. This scheme works very quickly while providing fine quality because it consists of standard functions in general GPU architecture. The experimental results show our method can generate a fine virtual view of an object by using multiple videos in real time.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10438399
• 書誌情報: 研究報告オーディオビジュアル複合情報処理（AVM）; 巻 2019-AVM-105, 号 11, p. 1-5, 発行日 2019-06-06
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8582
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会