Combining Point and Line Samples for Direct Illumination

2019 ◽  
Vol 38 (4) ◽  
pp. 159-169
Author(s):  
Katherine Salesin ◽  
Wojciech Jarosz
Keyword(s):  
Direct Illumination

scholarly journals ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

2021 ◽  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
State Of The Art ◽  
Image Decomposition ◽  
Natural Environments ◽  
Decomposition Algorithms ◽  
Ambient Light ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Direct Illumination

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.

scholarly journals Direct illumination

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

Accurate direct illumination using iterative adaptive sampling

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

THE PHOTO-ELECTRIC MEASUREMENT AND PHOTOGRAPHIC RECORDING OF DAYLIGHT

1931 ◽  
Vol 4 (6) ◽  
pp. 559-564 ◽  
Author(s):  
Wallace A. Thomson
Keyword(s):  
Time Of Day ◽  
Percentage Increase ◽  
The Sun ◽  
Photographic Recording ◽  
Remarkable Increase ◽  
Photographic Record ◽  
Clear Sky ◽  
Electric Measurement ◽  
Direct Illumination ◽  
Indirect Illumination

A method is described by which illumination intensities were measured by a photo-electric cell and galvanometer, and a continuous photographic record obtained of the variations of intensity over a period of time during which the ground was covered with snow.It was found that a remarkable increase in the illumination was caused by the presence of cloudiness with full sunshine. The percentage increase due to this condition in many cases was 20–30%, and on one occasion it was as high as 40%.When there was a cloud over the sun, with most of the sky clear, the decrease in illumination was found to vary up to 35%, depending on the density of the cloud, and on many occasions it was observed that the increase in indirect illumination due to overhead cloudiness more than balanced the decrease of direct illumination when the sun was partly hidden. From this it is concluded that the intensity may be greater with the sun partly hidden than at the same time of day with a clear sky.

Sign in / Sign up

Export Citation Format

Share Document