Raymarching Distance Fields with CUDA

Raymarching is a technique for rendering implicit surfaces using signed distance fields. It has been known and used since the 1980s for rendering fractals and CSG (constructive solid geometry) surfaces, but has rarely been used for commercial rendering applications such as film and 3D games. Raymarching was first used for photorealistic rendering in the mid 2000s by demoscene developers and hobbyist graphics programmers, receiving little to no attention from the academic community and professional graphics engineers. In the present work, we explain why the use of Simple and Fast Multimedia Library (SFML) by nearly all existing approaches leads to a number of inefficiencies, and hence set out to develop a CUDA oriented approach instead. We next show that the usual data handling pipeline leads to further unnecessary data flow overheads and therefore propose a novel pipeline structure that eliminates much of redundancy in the manner in which data are processed and passed. We proceed to introduce a series of data structures which were designed with the specific aim of exploiting the pipeline’s strengths in terms of efficiency while achieving a high degree of photorealism, as well as the accompanying models and optimizations that ultimately result in an engine which is capable of photorealistic and real-time rendering on complex scenes and arbitrary objects. Lastly, the effectiveness of our framework is demonstrated in a series of experiments which compare our engine both in terms of visual fidelity and computational efficiency with the leading commercial and open source solutions, namely Unreal Engine and Blender.

Visualization of construction infrastructure objects

Building information modeling provides an integrated three-dimensional environment applied to the management of large-scale engineering projects, allowing you to reduce the cost and time for planning structures and requirements for the reliability of buildings. The purpose of this work is to develop a methodology for changing the layout and reliability factor during the visualization of three-dimensional models to improve the analysis of building plans. This approach will allow you to combine different analytical methods and approaches when planning different structures. The results of this work suggest new directions for future research in the field of information visualization for the construction complex. The system is compatible with portable and scalable mobile devices. The proposed system can also be used for pre-project architecture and augmented visualization, where proprietary developed methods are used to achieve the quality of photorealistic rendering.

Combination of HBIM and UAV photogrammetry for modelling and documentation of forgotten heritage. Case study: Isabel II dam in Níjar (Almería, Spain)

The Isabel II dam is a monumental hydraulic structure built in the middle of the nineteenth century in Spain. In this study, unmanned aerial vehicle (UAV) photogrammetry was used as a data acquisition technique to carry out a survey of the dam’s current state and its surrounding constructions. The point cloud obtained by the photogrammetric process, together with the collected historical in-formation, served as the basis to generate an historic building information model (HBIM) that is the central core containing all the graphical, structural and archaeological information. The HBIM was validated by means of the As-Built for Autodesk Revit®-FARO® plug-in, and shows the high accuracy obtained with respect to the point cloud. The results show that with this methodology it is possible to obtain models representative of reality with an accuracy of ± 0.05 m. In addition, in order to improve the visualization, texture adjustments are made to obtain a photorealistic rendering of the model.

Structure Preserving Non-Photorealistic Rendering Framework for Image Abstraction and Stylization of Low-Illuminated and Underexposed Images

The proposed abstraction framework manipulates the visual-features from low-illuminated and underexposed images while retaining the prominent structural, medium scale details, tonal information, and suppresses the superfluous details like noise, complexity, and irregular gradient. The significant image features are refined at every stage of the work by comprehensively integrating a series of AnshuTMO and NPR filters through rigorous experiments. The work effectively preserves the structural features in the foreground of an image and diminishes the background content of an image. Effectiveness of the work has been validated by conducting experiments on the standard datasets such as Mould, Wang, and many other interesting datasets and the obtained results are compared with similar contemporary work cited in the literature. In addition, user visual feedback and the quality assessment techniques were used to evaluate the work. Image abstraction and stylization applications, constraints, challenges, and future work in the fields of NPR domain are also envisaged in this paper.

Gaussian Image Binarization

Line drawing and screentoning are two distinct areas of study in non-photorealistic rendering, where the former emphasizes object contours, while the latter conveys tone and shading information on object surfaces. As these two problems are concerned with different yet equally important features, either method seldom delivers a complete description of the scene when used alone. Yet, research community has largely treated them as separate problems and thus resulted in two entirely different sets of solutions, complicating both implementation and usage. In this paper, we present a stylistic image binarization method called hybrid difference of Gaussians (HDoG) that performs both line drawing and screentoning in a unified framework. Our method is based upon two different extensions of DoG operator: one for line extraction, and the other for tone description. In particular, we propose an extension called adaptive DoG, that uses luminance as weight to automatically generate screentone that adapts to the local tone. Experimental results demonstrate that our hybrid method effectively generates aesthetically pleasing image binarizations that encompass both line drawing and screentoning, closely resembling professional pen-and-ink illustrations. Also, being based on Gaussian filtering, our method is very fast and also easy to implement.

ALGORITMA NON-PHOTOREALISTIC RENDERING UNTUK KARTUN MENGGUNAKAN K-MEANS DAN CANNY

Cartoons are one type of illustration usually in a non-realistic or semi-realistic style. To make a cartoon drawing manually requires good drawing ability. So, not everyone can make cartoons. This research proposes a non-photorealistic rendering algorithm to create cartoon drawings automatically. The algorithm consists of four phases. First, create an image abstraction using bilateral filtering. Second, using kmeans clustering for abstract image quantization. Third, get the contour lines of the drawing using the canny algorithm. Fourth, contour lines and quantized images are combined. The results show that this algorithm can produce good visualization of cartoon images.

Variable photorealistic image synthesis for training dataset generation

Photorealistic rendering systems have recently found new applications in artificial intelligence, specifically in computer vision for the purpose of generation of image and video sequence datasets. The problem associated with this application is producing large number of photorealistic images with high variability of 3d models and their appearance. In this work, we propose an approach based on combining existing procedural texture generation techniques and domain randomization to generate large number of highly variative digital assets during the rendering process. This eliminates the need for a large pre-existing database of digital assets (only a small set of 3d models is required), and generates objects with unique appearance during rendering stage, reducing the needed post-processing of images and storage requirements. Our approach uses procedural texturing and material substitution to rapidly produce large number of variations of digital assets. The proposed solution can be used to produce training datasets for artificial intelligence applications and can be combined with most of state-of-the-art methods of scene generation.