| Creator |
|
|
|
|
|
|
|
| Language |
|
| Publisher |
|
|
|
| Date |
|
| Source Title |
|
| Vol |
|
| Issue |
|
| First Page |
|
| Last Page |
|
| Publication Type |
|
| Access Rights |
|
| Rights |
|
| Related DOI |
|
|
|
|
|
| Related URI |
|
|
|
|
|
| Relation |
|
|
|
|
|
| Abstract |
本稿では,3次元形状復元による自然な自由視点画像生成をPCクラスタを利用してオンラインで行う手法について述べる.提案するシステムでは,まず,対象形状を復元し,復元した形状を三角パッチ表現形式に変換する.次に,復元した対象形状表面の色情報を獲得し,最後に仮想視点位置に応じて自由視点画像を生成する.また,形状獲得の際には,形状の平滑化,対象形状に応じたボクセル空間の変形によりオンラインでの生成画像の高...精度化を図る.実験により,提案手法によって実時間でより高精度な自由視点画像の生成が可能となることを確認した.
In this paper, we present a system generating a free-viewpoint image effectively in real-time using multiple cameras and a PC-cluster. Our system firstly reconstructs a shape model of objects by the visual cone intersection method, secondly transforms the shape model represented in terms of a voxel form into a triangular patch form and smooths it, thirdly colors vertexes of triangular patches, and finally displays the shape-color model from the virtual viewpoint directed by a user. The key issue is 3D shape refinement to represent 3D object shapes more accurately without increase of processing time and memory space, which is effective to generate images with higher reality. Here, we describe implementation details of our system and show some experimental results.show more
|
Export Mendeley
UedaCVIM06