다객체 모델에 대한 사용자 중요도 기반 시점/조명 조절 기법

다국어 초록 (Multilingual Abstract)

In computer graphics, viewpoint selection for objects in a scene has been performed by evaluating the goodness of sampled viewpoints. Since the definition of a good viewpoint varies according to the user’s purpose, various measurements such as entropy and mesh saliency have been used. In this paper, we propose a method of selecting the best viewpoint and lighting for a multi-object scene, based on the user-assigned importance of each object. After sampling a viewpoint and lighting from the surrounding sphere of the scene, we render the images by combining the sampled viewpoint and lighting. We then select the best result that coincides with user-assigned importance by quantifying the saliency of each object in the rendered image. While this technique has the disadvantage of high computation cost due to the need to render combinations of viewpoints and lighting, it obtains the viewpoint and lighting most suitable for the user`s needs. In order to minimize the computation cost, an object-by-object pixel classification technique on GPU is also proposed in this paper.

참고문헌 (Reference)

1 Blanz, Volker, "What object attributes determine canonical views?" 28 (28): 575-599, 1999

2 Vazquez, Pere-Pau, "Viewpoint Selection using Viewpoint Entropy" 2001

3 Shtrom, Elizabeth, "Saliency Detection in Large Point Sets" 3591-3598, 2013

4 McMillan, Leonard, "Plenoptic modeling: an image-based rendering system" 1995

5 Weinshall, Daphna, "On View Likelihood and Stability" 19 : 97-108, 1997

6 Song, Ran, "Mesh saliency via spectral processing" 33 (33): 1-17, 2014

7 Chang Ha Lee, "Mesh saliency" Association for Computing Machinery (ACM) 24 (24): 659-, 2005

8 Gumhold, Stefan, "Maximum entropy light source placement" 275-282, 2002

9 Genova, Kyle, "Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes" 2017

10 Lun, Zhaoliang, "Elements of style: learning perceptual shape style similarity" 34 (34): 1-14, 2015

11 Laga, Hamid, "Data-driven approach for automatic orientation of 3D shapes" 27 : 977-989, 2011

12 Koulieris, George Alex, "C-LOD: Context-aware Material Level-of-Detail applied to Mobile Graphics" 33 : 41-49, 2014

13 Kamada, Tomihisa, "A simple method for computing general position in displaying three-dimensional objects" 41 : 43-56, 1988

14 Dutagaci, Helin, "A benchmark for best view selection of 3D objects" 2010

15 Bonaventura, "A Survey of Viewpoint Selection Methods for Polygonal Models" Entropy 2018