scholarly journals Direct Illumination Spherical Target Experiments

Author(s):  
Roy R. Johnson
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.


1979 ◽  
Vol 47 (6) ◽  
pp. 1983-1987 ◽  
Author(s):  
Takashi Abe ◽  
Koichi Kasuya ◽  
Keishiro Niu ◽  
Moritake Tamba

Nature ◽  
2000 ◽  
Vol 404 (6777) ◽  
pp. 454-454
Author(s):  
David Jones
Keyword(s):  

2006 ◽  
Vol 12 (3) ◽  
pp. 353-364 ◽  
Author(s):  
M. Donikian ◽  
B. Walter ◽  
Kavita Bala ◽  
S. Fernandez ◽  
D.P. Greenberg

Sign in / Sign up

Export Citation Format

Share Document