Search

The LivePaper system augments ordinary pieces of paper with projected information. Pages, cards and books are placed on an instrumented tabletop to activate their enhancement. To the user, it appears as if the paper gains new visual and auditory features. Projected annotations track the orientation and location of pages as the user moves them on the desktop. A piece of paper that is removed, but then returned to the desk, regains the same features that it previously exhibited. The LivePaper system accomplishes this by using features extracted from written material on the page, not from glyphs or other artificial marks. The paper describes both the system as a whole, and a number of sample applications we have developed to illustrate the feasibility of the LivePaper system. These applications include an architectural visualization tool, which projects a 3D hidden-line rendering of walls onto a page. The user may rotate and move the page to view the rendering from different angles. Another application is an audio player, which begins playing when a page (such as a business card) is laid on the desk. The user may control playback with his or her finger via projected buttons. Other applications include page-sharing, remote collaboration, and World Wide Web page viewing. From the user's perspective, all of these applications are attributes of the particular page, not features of the tabletop. Particular attention is given to the design of interaction: LivePaper is object-oriented, because the individual sheets are treated as computational units, but it also provides functions that involve several objects. The design principles applied to handle the different kinds of functionality are explained and illustrated in the LivePaper system, but are also proposed for wider use in augmented reality.

A practical technique is presented for efficiently rendering oriental black ink paintings with realistic diffusion effects, being based on models which simulate a variety of paper types and black ink properties. Strokes can be generated by bristles or elastic brush models simulating those actually used in oriental black ink painting. Incorporation of paper modeling allows users to draw on a wide variety of papers having either randomly generated fiber meshes or uniform meshes commonly found in fabrics which are also frequently used. This accordingly provides a unique platform for real-time dynamic simulation of realistic ink diffusion in that the resultant diffusion images reflect the texture and the global change of gray tones as well as local temporal variations specific to a particular paper. Examples are presented demonstrating the capability of the proposed technique for handling different ink and paper properties.

This research investigated the space compositions of Chernikhov’s 101 Architectural Fantasies via computer-aided simulation to interpret the relationships between architectural components and spatial organization. An algorithmic approach and a perception approach were tested. Traditional analysis emphasized the simulation of corresponding objects by perspective deconstruction methods, which might not be able to show the exactly correct spatial relationship between objects. This research adopted photogrammetry to investigate the non-orthogonal spatial construction of 3D objects in 2D pictures. Research results showed that the algorithmic approach may derive different degrees of angles of parallel or intersected objects, and that observers tend to be misled by the effect of “orthogonal assumption” in terms of their own visual experiences. This finding revealed that Chernikhov had created unreasonable descriptions of space. This result was verified by the existence of false parallel and orthogonal relationships between drawn building parts. Three tests were conducted. Observers used a reverse verification process to analyze three-dimensional objects re-built in simulation. The verification mirrored a two-way construction relationship between 2D perspective and 3D models.

This paper proposes a novel technique for converting a given animated mesh into a series of displaced subdivision surfaces. Instead of independently converting each mesh frame in the animated mesh, our technique produces displaced subdivision surfaces that share the same topology of the control mesh and a single displacement map. We first propose a conversion framework that enables sharing the same control mesh topology and a single displacement map among frames, and then present the details of the components in the framework. Each component is specifically designed to minimize the shape conversion errors that can be caused by enforcing a single displacement map. The resulting displaced subdivision surfaces have a compact representation, while reproducing the details of the original animated mesh. The representation can also be used for efficient rendering on modern graphics hardware that supports accelerated rendering of subdivision surfaces.

Modeling of realistic garments is essential for creating believable virtual environments. Sketch-based modeling of garments presents an appealing, easy to use alternative to the established modeling approaches which are time consuming and require significant tailoring expertise. Unfortunately, the results created using existing sketch-based methods lack realism. Driven by human perception of garment sketches, we propose a context-aware garment sketch interpretation based on a set of observations about key factors that affect the shape of garments. Based on this analysis we develop a geometric method for sketch-based modeling of garments which obtains more realistic results than previous techniques. We demonstrate the effectiveness of our method on a variety of inputs and validate our approach via a user study where viewers were asked to compare the believability of our outputs versus previous ones.

In recent years, there has been a growing interest in computer graphics and geometric modeling in the ability to create and manipulate seemingly impossible models (SIMs). Methods to create derivative work and modify drawings and paintings of SIMs made by artists were suggested. Similarly, 3D realization of SIMs of some of these drawings were also offered. In this work, we further explore the nature of SIMs and identify a class of SIMs that can be realized and modeled in 3D. As part of this analysis we show an invariance whose preservation allows one to model SIM artifacts that are completely realizable. We further present a mini-modeling package that allow end-users to realize whole new SIMs in two stages: modeling a regular 3D model and then converting it into a SIM using special deformations. We conclude with some examples, a discussion on the current limitations and a layout of possible future work.

A common variant of caricature relies on exaggerating characteristics of a shape that differs from a reference template, usually the distinctive traits of a human portrait. This work introduces a caricature tool that interactively emphasizes the differences between two three-dimensional meshes. They are represented in the manifold harmonic basis of the shape to be caricatured, providing intrinsic controls on the deformation and its scales. It further provides a smooth localization scheme for the deformation. This lets the user edit the caricature part by part, combining different settings and models of exaggeration, all expressed in terms of harmonic filter. This formulation also allows for interactivity, rendering the resulting 3d shape in real time.

Folding a thin sheet material such as paper along curves creates a developable surface composed of ruled surface patches. When using such surfaces in design, designers often repeat a process of folding along curves drawn on a sheet and checking the folded shape. Although several methods for constructing such shapes on a computer have been proposed, it is still difficult to check the folded shapes instantly from the crease patterns. In this paper, we propose a simple method that approximately realizes a simulation of curved folds with a triangular mesh from its crease pattern. The proposed method first approximates curves in a crease pattern with polylines and then generates a triangular mesh. In order to construct the discretized developable surface, the edges in the mesh are rearranged so that they align with the estimated rulings. The proposed method is characterized by its simplicity and is implemented on an existing origami simulator that runs in a web browser.

In recent years, with the improvement of artificial intelligence technology, it has become possible to reconstruct high-precision 3D human body models based on ordinary RGB images. The current 3D human body reconstruction technology requires complex external equipment to scan all angles of the human body, which is complicated to be implemented and cannot be popularized. In order to solve this problem, this paper applies deep learning models on reconstructing 3D human body based on monocular images. First of all, this paper uses Stacked Hourglass network to perform convolution operations on monocular images collected from different views. Then Multi-Layer Perceptrons (MLPs) are used to decode the encoded high-level images. The feature codes in the two views(main and side) are fused, and the interior and exterior points are classified by the fusion features, so as to obtain the corresponding 3D occupancy field. At last, the Marching Cube algorithm is used for 3D reconstruction with a specific threshold and then we use Laplace smoothing algorithm to remove artifacts. This paper proposes a dense sampling strategy based on the important joint points of the human body, which has a certain optimization effect on the realization of high-precision 3D reconstruction. The performance of the proposed scheme has been validated on the open source datasets, MGN dataset and the THuman dataset, provided by Tsinghua University. The proposed scheme can reconstruct features such as clothing folds, color textures, and facial details,and has great potential to be applied in different applications.

Gears play a pivotal role in machine design. This paper proposes an algorithm to simplify the shapes of planar gears. This is achieved via iterative conjugation, using precise algebraic sweeps. The notion of shape simplification is introduced in a mathematically rigorous manner and it is shown that the conjugation process converges, yielding a pair of meshing gears that follow the desired motion. Simplified gear shapes may lead to improved mechanical characteristics and reduction in manufacturing costs. The generality of algebraic sweeps allows precise design of gears with freeform shapes and non-uniform motion transmission. Moreover, the computational framework proposed in this paper is versatile, with applications beyond gear design. A variety of examples from an implementation of our algorithm, that offers topological guarantees, are presented, which demonstrate the robustness and efficacy of our approach.

In this paper, we present a novel adaptive particle resampling method tailored for surface reconstruction of level-sets defined by the boundary particles from a particle-based liquid simulation. The proposed approach is simple and easy to implement, and only requires the positions of the particles to identify and refine regions with small and thin fluid features accurately. The method comprises four main stages: boundary detection, feature classification, particle refinement, and surface reconstruction. For each simulation frame, firstly the free-surface particles are captured through a boundary detection method. Then, the boundary particles are classified and labeled according to the deformation and the stretching of the free-surface computed from the Principal Component Analysis (PCA) of the particle positions. The particles placed at feature regions are then refined according to their feature classification. Finally, we extract the free-surface of the zero level-set defined by the resampled boundary particles and its normals. In order to render the free-surface, we demonstrate how the traditional methods of surface fitting in Computer Graphics and Computational Physics literature can benefit from the proposed resampling method. Furthermore, the results shown in the paper attest the effectiveness and robustness of our method when compared to state-of-the-art adaptive particle resampling techniques.

This special issue contains extended and revised versions of the best papers presented at the 7th Conference on Smart Tools and Applications in Graphics (STAG 2020), held virtually on November 12–13, 2020. The two selected papers cover two different visual computing domains. The first contribution proposes a novel Level-of-Detail data structure (Motion Tree) to efficiently render motion blur of animated objects, while the second contribution presents an evaluation of current deep-learning based 3D registration solutions.

Although 3D Voronoi diagrams and medial axis transforms have numerous applications in biology, robotics, and manufacturing, most researchers use Voronoi diagrams of points instead of the true 3D input geometry, due to issues of robustness and scalability. In this paper, we present a robust sample-based GPU algorithm for calculating the full topology of Voronoi diagrams of non-general position spheres. Prior work demonstrated that the presence, geometry, and combinatorial basis of spheres that contribute to Voronoi vertices can be efficiently computed by shooting rays from each input sphere, mapping ray intersections with the nearest bisector surface to parametric bounding cubes, and analyzing the results. In this paper, we propose an algorithm on this parametric bounding cube to compute Voronoi edges in addition to the vertices. We successfully extract the full topology of the Voronoi diagram, including special cases such as isolated Voronoi edges that do not contain Voronoi vertices, more than three Voronoi edges emanating from a Voronoi vertex, and Voronoi edges that are shared by more than three Voronoi cells. Our GPU implementation efficiently and robustly handles all input, whether in general or non-general position, and finds all Voronoi vertices and edges, modulo the sampling density, including isolated disconnected edges.

User studies are indispensable for visualization application papers in order to assess the value and limitations of the presented approach. Important aspects are how well depth and shape information can be perceived, as coding of these aspects is essential to enable an understandable representation of complex 3D data. In practice, there is usually little time to perform such studies, and the establishment and conduction of user studies can be labour-intensive. In addition, it can be difficult to reach enough participants to obtain expressive results regarding the quality of different visualization techniques. In this paper, we propose a framework that allows visualization researchers to quickly create task-based user studies on depth and shape perception for different surface visualizations and perform the resulting tasks via a web interface. With our approach, the effort for generating user studies is reduced and at the same time the web-based component allows researchers to attract more participants to their study. We demonstrate our framework by applying shape and depth evaluation tasks to visualizations of various surface representations used in many technical and biomedical applications.

This paper proposes a hybrid Lagrangian–Eulerian method involving all participating media for high-speed fluid simulation and its accompanying phenomena. We take advantages of both particle- and grid-based solvers in our new approach by dividing all the physical states into two different parts based on their individual characteristics. Lagrangian-based solver gives rise to liquid, droplet, and foam creation and facilitates the drastic shape distortion and state transition during the multi-physical processes simulation from the perspective of individual particles. At the same time, Eulerian-based solver mainly focuses on the animation of spray, which enables a fog-like atmosphere. Essential to all of the aforementioned functionalities is the state transition among different media considering both physical and geometric features in this paper. The state transition enables to streamline the dis-association and generation of certain physical states. Moreover, to ensure the synchronization of hybrid models, we establish essential interaction and build tight coupling between the particle- and grid-based subsystems. With the comprehensive experimental results, we have manifested that our new modeling approach is both effective and highly modularized, and is capable of producing convincing visual effects for a wider range of graphics and animation tasks.

In this paper, we review Augmented Reality Training systems and how they can be combined with Intelligent Tutoring Systems to improve pedagogical outcomes on spatial learning tasks. Intelligent Tutoring Systems (ITSs) are computer-based systems that provide personalised feedback, learner support and task selection by modelling learner knowledge. They have been shown to significantly improve learning, however currently provide little support for psychomotor tasks that involve spatial learning. For such tasks, ITSs may not be able to present instruction in an intuitive manner for mental model reconstruction. Augmented Reality (AR) overlays 3-Dimensional virtual objects on the real world, and has been shown to be useful for training in physical manipulation tasks. However, most current AR training systems provide only step by step instructions and do not adapt training content to user needs. In this paper we show how combining ITS with AR systems has the potential to overcome the limitations of both approaches and produce a significantly improved learning experience. We provide examples of previous work in this area, and provide guidelines for future AR ITS systems. Refereed/Peer-reviewed

This paper describes a group of auxetic-inspired material structures that can transform into various shapes upon compression. We developed four cellular-based material structure units composed of rigid plates and elastic/rotary hinges. Different compositions of these units lead to a variety of tunable shape-changing possibilities, such as uniform scaling, shearing, bending and rotating. By tessellating those transformations together, we can create various higher level transformations for product design. In the paper, we first give a geometrical and numerical description of the units’ configuration and their degrees of freedom. An interactive simulation tool is developed for users to input designed structures and preview the transformation. Finally we present three application prototypes that utilize our proposed structures.

Object skeleton is a useful geometric tool for shape analysis tasks. It encodes the topological structure of the primitive shape and preserves a geometric cue as well. Skeletonization is a seemingly simple but difficult research problem. A desirable skeletonization algorithm has to be topologically complete, insensitive to boundary noise, without any branch pruning and free of user-specified parameters. In this paper, we propose a novel method based on the heat equation to extract skeletons assuming that the input is a binary image. Based on the connection between the skeleton and ridge lines, we use the smooth heat diffusion height surface to approximate the real distance field, and then extract the ridge lines of the surface as the output skeleton. Different from the existing approaches, the proposed method in this paper has the above-mentioned excellent properties and can capture the clean and stable skeleton directly. Extensive experimental results show that the new approach can yield better skeletons than the state-of-the-art.

The animation of articulated characters is a central problem in the computer graphics field. Skeletal animation techniques define a workflow which has proven to be effective for boundary representations (B-Reps). This paper extends the classical skeletal animation pipeline to deal with characters internal tissues. In contrast to most common approaches, the proposed technique automates all the stages of this workflow. Well known skinning algorithms, such as Linear Blending Skinning, Dual Quaternion Skinning or Optimized Centers of Rotation were adapted to allow the use of our technique in applications where interactivity is required. The pipeline proposed in this paper can be used in many computer graphics systems such as games or educational applications to visualize and animate the internal anatomy of a virtual character at interactive rates.

Based on the physically-based clothing simulation, this paper develops a novel method to customize the fit of the given garment to the reference body. The method defines three misfit measures, namely the landmark point misfit, landmark line misfit, and circumferential misfit, based on the correspondence between the landmark points and landmark lines in the body and garment. In terms of the above misfit measures, this paper proposes the heuristic misfit reduction method. The heuristic misfit reduction method works in the following way. Starting from a given preliminary garment, it (1) performs the fit evaluation, (2) modifies the panels based on the evaluation to enhance the fit, then (3) performs the draping simulation with the modified panels. The procedure is repeated until a satisfactory fit is achieved. According to our experiments, the proposed method successfully customizes a given garment to fit to the given body.

The primary purpose of this paper is to realize robust place recognition algorithms towards simultaneous viewpoint and condition changes, and provide satisfactory computational efficiency. In this paper, we significantly improve the viewpoint invariance of the SeqSLAM algorithm by using state-of-the-art deep learning techniques to generate robust feature representations of images and develop the SeqCNNSLAM. Experimental results show that SeqCNNSLAM outperforms state-of-the-art place recognition systems in most cases, such as, when precision is maintained at 100%, the maximum recall obtained by SeqCNNSLAM is 50% higher than SeqSLAM on the Norland dataset with simultaneous condition change and 12.5% viewpoint change. Besides, we develop an acceleration method called A-SeqCNNSLAM, which exploits the location relationship between the matching images of adjacent images to reduce the matching range of the current image. Experimental results demonstrate that an acceleration of ∼ 5 times is achieved with minimal accuracy degradation of ∼ 5%. Finally, to enable A-SeqCNNSLAM adaptability in new environments, O-SeqCNNSLAM is devised for the online parameter adjustment in A-SeqCNNSLAM.

Digital images are ubiquitous in our modern lives, with uses ranging from social media to news, and even scientific papers. For this reason, it is crucial evaluate how accurate people are when performing the task of identify doctored images. In this paper, we performed an extensive user study evaluating subjects capacity to detect fake images. After observing an image, users have been asked if it had been altered or not. If the user answered the image has been altered, he had to provide evidence in the form of a click on the image. We collected 17,208 individual answers from 383 users, using 177 images selected from public forensic databases. Different from other previously studies, our method propose different ways to avoid lucky guess when evaluating users answers. Our results indicate that people show inaccurate skills at differentiating between altered and non-altered images, with an accuracy of 58%, and only identifying the modified images 46.5% of the time. We also track user features such as age, answering time, confidence, providing deep analysis of how such variables influence on the users' performance.

This paper presents a direct stylization system to render 3D animated geometry as watercolor painted animation. Featuring low-level art-direction in real-time, our approach focuses on letting users paint custom stylization parameters in the 3D scene. These painted parameters drive watercolor effects in object-space, managing localized control and emulating the characteristic appearance of traditional watercolor. For this purpose, the parameters alter the object-space geometric representations and are rasterized, to coherently control and enhance further image-space effects. The watercolor effects are simulated through improved and novel algorithms to recreate hand tremors, pigment turbulence, color bleeding, edge darkening, paper distortion and granulation. All these represent essential characteristic effects of traditional watercolor. The proposed direct stylization system scales well with scene complexity, can be implemented in most rendering pipelines and can be adapted to simulate a wide range of watercolor looks. The simulation is compared to previous approaches and is evaluated through a user study, involving professional CG artists spending over 50 h stylizing their own assets and sharing their feedback about the watercolor stylization, the direct stylization system and their needs as artists using Non-photorealistic Rendering (NPR). Accepted version

Flexible visual analysis of long, high-resolution, and irregularly sampled time series data from multiple sensor streams is a challenge in several domains. In the field of additive manufacturing, this capability is critical for realizing the full potential of large-scale 3D printers. In this paper, we propose a visual analytics approach that helps additive manufacturing researchers acquire a deep understanding of patterns in log and imagery data collected by 3D printers. Specific goals include discovering patterns related to defects and system performance issues, optimizing build configurations to avoid defects, and increasing production efficiency. We introduce Falcon, a new visual analytics system that allows users to interactively explore large, time-oriented data sets from multiple linked perspectives. Falcon provides overviews, detailed views, and unique segmented time series visualizations, all with adjustable scale options. To illustrate the effectiveness of Falcon at providing thorough and efficient knowledge discovery, we present a practical case study involving experts in additive manufacturing and data from a large-scale 3D printer. Although the focus of this paper is on additive manufacturing, the techniques described are applicable to the analysis of any quantitative time series.

This paper discusses the creation of star effects in captured night-time photos based on using depth information available by stereo vision. Star effects are an important design factor for night-time photos. Modern imaging technologies support that night-time photos can be taken free-hand, but star effects are not achievable for such camera settings. Self-calibration is an important feature of the presented star-effect simulation method. A photographer is assumed to take just an uncalibrated stereo image pair (i.e. a base and a match image), for example by taking two photos subsequently (e.g. by a mobile phone at about the same pose). For self-calibration we apply the following routine: extract a family of pairs of feature points, calibrate the stereo image pair by using those feature points, and calculate depth data by stereo matching. For creating the star effects, first we detect highlight regions in the base image. Second, we estimate the luminance according to available depth information. Third, we render star patterns with a chosen input texture. Basically we provide a complete tool which is easy to apply for the generation of a user-selected star texture. Minor variations can be introduced in star pattern rendering in order to achieve more natural and vivid looking star effects. By extensive experiments we verified that our rendering results are potentially similar to real-world star effect photos. We demonstrate some of our results, also for illustrating that they appear more natural than results achieved by existing commercial applications. We also illustrate that our method allows us to render more artistic star patterns not available in recorded photographs. In brief, this paper reports research on automatically simulating both photorealistic and non-photorealistic star effects.

Folding planar sheets to make 3D shapes from is an ancient practice with many new applications, ranging from personal fabrication of customized items to design of surgical instruments for minimally invasive surgery in self-folding machines. Given a polyhedral mesh, unfolding is an operation of cutting and flattening the mesh. The flattened polyhedral nets are then cut out of planar materials and folded back to 3D. Unfolding a polyhedral mesh into planar nets usually require segmentation. Either used as a preprocessing step to simplify the mesh and provide semantics or as the result of unfolding to avoid overlapping, the segmentation and the unfolding operations are decoupled. Consequently, segmented components may not be unfoldable and unfolded nets usually provide no semantic meaning and make folding difficult. In this paper, we propose a strategy that tightly couples unfolding and segmentation. We show that the proposed method produces unfoldable segmentation that resembles carefully designed paper craft. The key idea that enables this capability is an algorithm that learns from failed unfoldings. Graphical abstractDisplay Omitted HighlightsWe propose a strategy that produces unfoldable segmentation via failed unfoldings.Our unfoldable segmentation provides shape semantics and convexity.Shape semantics in the proposed segmentation eases the fabrication process.High convexity allows higher proability of finding collision-free folding path.Collision-free folding path is critical in developing a self-folding machine.

Mesh saliency was introduced and joined the community of computer graphics ten years ago, which can benefit various applications, for instance, mesh reduction, mesh segmentation, self-similarity matching, scan integration, volume rendering, 3D printing, etc. Before, saliency detection had been successfully applied to image processing and pattern recognition to study how the world is perceptually intelligible for robots. In contrast to color of images and coherence of videos, geometric signals are defined with two-dimensional manifolds whose discrete representation is irregular, leading differences to the nature and difficulties to the solution of mesh saliency. To tackle the challenge, the last decade has witnessed significant advances in mesh saliency detection. However, a survey of recent advances in mesh saliency detection as well as its applications does not yet exist to date. This paper provides a first and comprehensive reference source of shape context based mesh saliency for researchers from a wide range of domains, including but not limited to computer graphics and vision. It reviews main contributions, advantages, drawbacks, and applications of known mesh saliency detection methods and discusses current trends and outlook for future study. Graphical abstractDisplay Omitted HighlightsThe paper provides the first and comprehensive reference resource of mesh saliency.35 representative methods published from 2005 to 2015 are viewed.4 key insights into the topic are presented, and open problems are raised.

Tracking is an important task that is used for several applications, such as navigation assistance and augmented reality. The improvement and popularization of mobile devices in recent years allowed these applications to be executed on such devices. Thus, several tracking techniques proposed lately take into consideration the benefits and limitations of handheld devices. Therefore, the goal of this work is to perform a systematic mapping in order to provide trends and classification regarding the recent publications in the area of tracking for mobile devices. This study collected 2276 papers from three scientific databases using an open-source crawler, from which 360 were selected to be classified according to four properties: tracking type, degree of freedom, tracking platform and research type. The analysis of these data resulted in a map of the research field, which was presented under three perspectives: the distribution and trends over time of each classification property and the relationship between them. Besides the visual map, the full list of classified papers is available through an open-source web-based catalog. The results showed that the number of publications is increasing every year, which shows a growing interest in this field. Moreover, most works use the device's sensors for tracking in location-based applications and almost all of them calculate a 2D or 2D + ? pose. There are also several papers about vision-based techniques to compute the device's pose and in the majority of them a full 6D pose is computed. Beyond that, there is a clear preference for systems that calculate the pose locally on the device and only a few use a remote server to assist in this task. Moreover, more than 92% of all papers propose a new technique or use existing ones to create a solution. Graphical abstractDisplay Omitted HighlightsIdentification of the relevant studies in tracking for mobile devices.Classification schema of the field.Systematic map of the existing research in the area.Discussion about the major findings of this study.Web application with a catalog of classified studies that is collaboratively updated.

Indirect illumination is an essential part of realistically rendering virtual scenes. In this paper we present a new method for computing multi-bounce indirect illumination for diffuse surfaces which is particularly well-suited for indoor scenes with complex occlusion, where an appropriate simulation of the indirect illumination is extremely important. The technique presented in this paper combines the benefits of shooting methods with the concept of photon mapping to compute a convincing light map for the scene with full diffuse lighting effects. The main idea is to carry out a multi-bounce light distribution almost entirely on the GPU using a shooting approach with virtual point lights. The final result is then stored in a texture atlas by projecting the energy from each virtual point light into the texels visible from its perspective. The technique uses only few resources on the graphics card and is flexible in the sense that it can easily be adjusted for either quality or speed, allowing the user to create convincing results in a matter of seconds or minutes, depending on the scene complexity. Graphical abstractDisplay Omitted HighlightsApproximating a physically correct light distribution with multiple bounces.Developing a progressive refinement algorithm for virtual point lights on the GPU.Creating a high-resolution light atlas with a special projection method on the GPU.