Illumination for computer generated pictures

By Bui Tuong Phong. 1975

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, methodology): “To generate rendered views of polygon meshes, we use the Phong reflection model [27].”
FusionNet: 3D Object Classification Using Multiple Data Representations (2016, methodology): “Phong reflection method was used to obtain all 2D projections [17]”
Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories (2016, methodology): “A modiﬁed Phong reﬂectance model [24, 17] is assigned to objects to generate photo-realistic shading and specular effects.”
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images (2018, methodology): “domized diffuse and specular reflection (simple Phong model [27] in OpenGL), (2) inserting random background images from the Pascal VOC dataset [6], (3) varying image contrast, brightness, Gaussian blur and color distortions, (4) applying occlusions using random object masks or black squares.”
Experimental analysis of BRDF models (2005, background): “Eurographics Symposium on Rendering (2005) Kavita Bala, Philip Dutré (Editors)”
Image change detection algorithms: a systematic survey (2005, background): “…For images of scenes containing Lambertian surfaces, the observed image intensity at a pixel can be modeled as the product of two components: the illumination from the light source(s) in the scene and the reflectance of the object surface to which belongs (2) This is called the shading model [46].”
Unsupervised Training for 3D Morphable Model Regression (2018, methodology): “We use the Phong reflection model [19] for shading.”
Sky-View Factor as a Relief Visualization Technique (2011, methodology): “There are numerous analytical hill-shading techniques [14-18]; however only the method developed by Yoëli [19] became a standard feature in most GIS software.”
3D Face Reconstruction by Learning from Synthetic Data (2016, methodology): “We use Phong reflectance [19] for modeling the shading.”
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (2021, unknown): “For BRDFs that are rotationally-symmetric about the re-ﬂected view direction, i.e . ones that satisfy f (ˆ ω i , ˆ ω o ) = p (ˆ ω r · ˆ ω i ) for some lobe function p (which includes BRDFs such as Phong [28]), and neglecting phenomena such as in-terreﬂections and self-occlusions, view-dependent radi”
A comparative study on shadow compensation of color aerial images in invariant color models (2006, methodology): “[12] presented an imaging model of shadows based on Phong illumination model [13] and employed thresholding on the hue, blue, and green-blue difference components sequentially to detect shadowed areas, which were then compensated by applying the Retinex technique to both shadowed and nonshadowed are”
A data-driven reflectance model (2003, methodology): “reflectance models [ 41 , 55, 25] provide the BRDFs used in computer graphics and com-”
Ambient Occlusion and Edge Cueing for Enhancing Real Time Molecular Visualization (2006, background): “The commonest and cheapest solution [23] is to use a simple per-scene constant term, but this approach leads to a notable flatness in the portions of the scene which are not directly lit.”