Introduction

Pharr, Matt; Jakob, Wenzel; Humphreys, Greg

doi:10.1016/b978-0-12-800645-0.50001-4

Cited by 84 publications

(142 citation statements)

References 0 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…"The goal of photorealistic rendering is to create an image of a 3D scene that is indistinguishable from a photograph of the same scene". 2 To this quote Pharr et al note that the word "indistinguishable" itself is inaccurate, because it subjectively depends on the observer. But the goal is pursued by using natural laws of material-dependent light propagation reflection and refraction to model the scene appearance in a physically correct way.…”

Section: Definition Of Terms and Methodology Of Literature Researchmentioning

confidence: 99%

“…The outgoing radiance L (p, ω 0 ) from a point p in direction ω 0 is equal to the emitted radiance at that point in that direction, L i (p, ω i ) plus the incident radiance from all directions on the sphere S 2 around p scaled by the BSDF * f (p, ω 0 , ω i ) and a cosine term. [2][3][4] Figure 1: Computer generated image using physically based rendering like path tracing from Pharr et al 2 Ray Tracing In ray tracing a ray is sent out from the virtual camera into the scene and traced until it intersects with a solid body. At this point a ray is cast to each of the light sources in the scene to calculate illumination and surface shading for the intersection point.…”

Section: Definition Of Terms and Methodology Of Literature Researchmentioning

confidence: 99%

See 1 more Smart Citation

Physically based synthetic image generation for machine learning: a review of pertinent literature

Schraml

2019

Photonics and Education in Measurement Science 2019

View full text Add to dashboard Cite

The term deep learning is almost on everyone's lips these days, in the area of computer vision mainly because of the great advances deep learning approaches have made amongst others in object detection and classification. For general object localization or classification tasks there do exist several giant databases containing several millions of labeled images and several thousands of different labels like COCO and ImageNet. In contrast in industrial applications like quality inspection there do hardly ever exist such training data not only for reasons of confidentiality of trade secrets. An obvious way to remedy this deficiency is the synthetic creation of image data. Physically based rendering attempts to achieve photorealistic images by accurately simulating the flow of light of the real world according to various physical laws. Therefor multiple techniques like Ray Tracing and Path Tracing have been implemented and are becoming increasingly widespread as hardware performance increases. The intent of this article is to give a wide but nevertheless preferably comprehensive overview of which approaches have been pursued in recent literature to generate realistic synthetic training images. The development of various rendering methods from rasterization to bidirectional monte carlo path tracing is outlined, as well as their differences and use. Along with the terminology a few mathematical foundations like the Bidirectional Reflectance Distribution Function (BRDF) are briefly described. Altogether special concern is given to industrial data and quality control, comparing literature and the practical application of its results.

show abstract

Section: Definition Of Terms and Methodology Of Literature Researchmentioning

confidence: 99%

Section: Definition Of Terms and Methodology Of Literature Researchmentioning

confidence: 99%

Physically based synthetic image generation for machine learning: a review of pertinent literature

Schraml

2019

Photonics and Education in Measurement Science 2019

View full text Add to dashboard Cite

show abstract

“…As all the radii are the same, these primitives will always fit perfectly together, creating the appearance of a single connected streamline. Implementing this approach is straightforward: ray-sphere and ray-cylinder intersections are well described in the literature [Dra99, PJH16], and building an acceleration structure on these primitives can be left to Embree.…”

Section: Methods Overviewmentioning

confidence: 99%

“…When the control points have the same radii, it is sufficient to link them with a cylinder; however, if the radii differ, we must use a cone stump. Ray-sphere, ray-cylinder, and ray-cone intersections are well described in the ray tracing literature [PJH16, Dra99]. Bhagvat et al [BJCW09] presented a similar approach for ray-conical frusta intersection; however, our definition of a cone stump is not identical to a conical frusta.…”

Section: Methodsmentioning

confidence: 99%

Ray Tracing Generalized Tube Primitives: Method and Applications

Han

Wald

Usher

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

We present a general high-performance technique for ray tracing generalized tube primitives. Our technique efficiently supports tube primitives with fixed and varying radii, general acyclic graph structures with bifurcations, and correct transparency with interior surface removal. Such tube primitives are widely used in scientific visualization to represent diffusion tensor imaging tractographies, neuron morphologies, and scalar or vector fields of 3D flow. We implement our approach within the OSPRay ray tracing framework, and evaluate it on a range of interactive visualization use cases of fixed- and varying-radius streamlines, pathlines, complex neuron morphologies, and brain tractographies. Our proposed approach provides interactive, high-quality rendering, with low memory overhead.

show abstract

“…Several points of view of commonly used 3D scenes [ 43 ] were calculated with several levels of samples. The rendering engine used was PBRT (for Physically Based Rendering) version 3 [ 44 ] and only one integrator (Path Tracing) has been used among the various available, both because of its wide use and to avoid the biases that could arise when using different integrators.…”

Section: Subjective Dataset Collectionmentioning

confidence: 99%

Stopping Criterion during Rendering of Computer-Generated Images Based on SVD-Entropy

Buisine

Bigand

Synave

et al. 2021

Entropy

View full text Add to dashboard Cite

The estimation of image quality and noise perception still remains an important issue in various image processing applications. It has also become a hot topic in the field of photo-realistic computer graphics where noise is inherent in the calculation process. Unlike natural-scene images, however, a reference image is not available for computer-generated images. Thus, classic methods to assess noise quantity and stopping criterion during the rendering process are not usable. This is particularly important in the case of global illumination methods based on stochastic techniques: They provide photo-realistic images which are, however, corrupted by stochastic noise. This noise can be reduced by increasing the number of paths, as proved by Monte Carlo theory, but the problem of finding the right number of paths that are required in order to ensure that human observers cannot perceive any noise is still open. Until now, the features taking part in the human evaluation of image quality and the remaining perceived noise are not precisely known. Synthetic image generation tends to be very expensive and the produced datasets are high-dimensional datasets. In that case, finding a stopping criterion using a learning framework is a challenging task. In this paper, a new method for characterizing computational noise for computer generated images is presented. The noise is represented by the entropy of the singular value decomposition of each block composing an image. These Singular Value Decomposition (SVD)-entropy values are then used as input to a recurrent neural network architecture model in order to extract image noise and in predicting a visual convergence threshold of different parts of any image. Thus a new no-reference image quality assessment is proposed using the relation between SVD-Entropy and perceptual quality, based on a sequence of distorted images. Experiments show that the proposed method, compared with experimental psycho-visual scores, demonstrates a good consistency between these scores and stopping criterion measures that we obtain.

show abstract

Introduction

Cited by 84 publications

References 0 publications

Physically based synthetic image generation for machine learning: a review of pertinent literature

Physically based synthetic image generation for machine learning: a review of pertinent literature

Ray Tracing Generalized Tube Primitives: Method and Applications

Stopping Criterion during Rendering of Computer-Generated Images Based on SVD-Entropy

Contact Info

Product

Resources

About