A line-integration based method for depth recovery from surface normals
作者： Zhongquan Wu , Lingxiao Li
DOI: 10.1016/0734-189X(88)90042-4
关键词:
摘要: Abstract This paper describes a new method for constructing depth map from surface normals. In this recovery method, an arbitrary must be first preset point somewhere in the image, then path-independent line integrals are computed to get relative depths at every pont image. The validity of proposed is discussed and its efficiency was tested using normals obtained by shape shading algorithm. comparison previous ones given. Theoretical analysis experimental results show that our both powerful easy implement.
elsevier.com
sci-hub.se 参考文章(4)
Katsushi Ikeuchi, Berthold K.P. Horn, Numerical shape from shading and occluding boundaries Artificial Intelligence. ,vol. 17, pp. 141- 184 ,(1981) , 10.1016/0004-3702(81)90023-0
Andrew P. Witkin, Recovering surface shape and orientation from texture Artificial Intelligence. ,vol. 17, pp. 17- 45 ,(1981) , 10.1016/0004-3702(81)90019-9
E. North Coleman, Ramesh Jain, Obtaining 3-dimensional shape of textured and specular surfaces using four-source photometry Computer Graphics and Image Processing. ,vol. 18, pp. 309- 328 ,(1982) , 10.1016/0146-664X(82)90001-6
H.G. Barrow, J.M. Tenenbaum, Interpreting line drawings as three-dimensional surfaces Artificial Intelligence. ,vol. 17, pp. 75- 116 ,(1981) , 10.1016/0004-3702(81)90021-7