Vladimir Alexandrovich Frolov's research while affiliated with Russian Academy of Sciences and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (31)
We propose new image representations that saves sub-pixel borders between objects. This provides a number of benefits in 4 scenarios: (1) anti-aliasing, (2) up-sampling, (3) de-noising, (4) differentiable rendering. For pixels containing borders, we store information about these borders using a small BSP tree. This allows us to restore the geometri...
The main purpose of this investigation is to use information from previous frames for partial synthesis of the new one. Algorithms utilizing already calculated information have become an integral part of many interactive applications in recent years, and using of such methods allows reduces the computational load on the GPU without significantly de...
Vector images provide a resolution independent representation that can be efficiently scaled to any resolution. However, there is no ready-to-use solution for supporting vector texturing in GPU based photorealistic rendering systems. In this work we present the experience of implementing support for vector textures in such rendering system using tw...
Modeling and rendering large scenes with thousands of plants is still a challenging problem. Geometric models of individual plants consist of millions of triangles each and their complexity must be reduced in advance to make real-time rendering possible. Existing solutions usually implemented as a part of plants generator, make an ecosystem simulat...
The field of light transport simulation quickly growths in last decades. Nowadays there are about hundreds of books and papers that are quite difficult to cover for applied researcher or developer. Unlike similar surveys, in this paper we make attempt to provide short roadmap to select the best method for some light transport problem based on scene...
Screen-space Ambient Occlusion (SSAO) methods have become an integral part of the process of calculating global illumination effects in real-time applications. The use of ambient occlusion improves the perception of the geometry of the scene, and also makes a significant contribution to the realism of the rendered image. However, the problems of ac...
In this paper we propose exemplar-based 3D texture synthesis method which unlike existing neural network approaches preserve structural elements in texture. The proposed approach does this by accounting additional image properties which stand for the preservation of the structure with the help of a specially constructed error function used for trai...
We propose a novel high-level approach for software development on GPU using Vulkan API. Our goal is to speed-up development and performance studies for complex algorithms on GPU, which is quite difficult and laborious for Vulkan due to large number of HW features low level details. The proposed approach uses auto programming to translate ordinary...
There are a lot of methods for rendering of shell-space geometry, represented through voxel texture, known for today. While the topic is well studied in terms of techniques for applying this geometry onto surfaces, a little attention was paid to representation of sub-pixel details of the geometry. Such details are prone to produce aliasing artifact...
Since the creation of computers, there has been a lingering problem of data storing and creation for various tasks. In terms of computer graphics and video games, there has been a constant need in assets. Although nowadays the issue of space is not one of the developers' prime concerns, the need in being able to automate asset creation is still rel...
The paper proposes a number of methods that can be used to synthesize images of interiors in order to train artificial intelligence. The proposed methods solve the problem of generating training samples in a complex, starting from automatic generation of 3D content and ending with rendering directly. One of the main goals of the develioed system is...
In this paper we present an approach to image datasets generation based on photorealistic rendering with controlled parameter randomization of 3d scenes. These datasets can be used, for example, for training artificial intelligence models in computer vision. We describe the architecture of system implementing proposed approach and show examples of...
In this paper we address the problem of determining the detail level of precomputed procedural textures for photorealistic rendering. We propose an approach based on a fast preliminary scene visualization with level of detail calculation based on mip-mapping. Proposed solution was tested for computing resolution of different types of procedural tex...
Integration layer between digital content creation software (DCCS) and rendering software in a form of specialized database is proposed in this paper. In our approach, we focus on providing fast 3D-scene updates, ability to work with large digital assets (not fitting into memory), importing and exporting arbitrary parameters, serialization, conveni...
A software implementation of the graphics library OpenGL SC (Safety Critical) for the promising real-time onboard operating system JetOS for Russian aircraft is considered. The library development adheres to the international standards. The library must support multicore CPUs and be platform independent. The use of software implementation considera...
Solutions to the key problems of Metropolis light transport implementation on GPUs are proposed. A “burn-in” method relying on the ordinary Monte Carlo method, owing to which the “startup bias” is significantly reduced, is suggested. Memory optimizations methods (including multiple proposal Metropolis light transport) are proposed, and technical as...
Monte Carlo Path Tracing is a core light transport technique which is used for modern methods (like BDPT, MLT, VCM and others). One of the main challenge of efficient GPU Path Tracing implementation is inefficient workload caused by paths of different lengths; few threads process the long paths, while other threads are idle. A work distribution tec...
The paper proposes a new high-quality approach to fast Monte-Carlo path-tracing. The key feature of the approach is screen-space filtering with the help of additional information (depth, normal direction, etc.) of the illumination separated from material color. It allows to reach high-quality and edge-aware filtering. The proposed method yields 1–2...
This paper introduces an efficient and simple algorithm for constructing Multiple Reference (MR) octrees on a GPU in application to Photon Mapping and Irradiance Caching techniques. Although MR-octrees are hierarchical structures, we successfully ignore their hierarchical nature and present an approach with plain construction, compact data layout a...
This work presents an approach for biased photorealistic rendering on graphics processor units (GPUs). The key idea of the approach is to combine irradiance caching with coherent adaptive path tracing.
Citations
... Many routine tasks, that in OpenGL the driver is responsible for (GPU memory management, command queueing, frame buffering, etc.), in Vulkan must be implemented by a developer, which significantly complicates graphics programming. Various solutions have been proposed to get around this problem: the V-EZ auxiliary shell [9], pattern-based development automation [10], the VulkanSceneGraph wrapper library [11], etc. These solutions are united by application development implementing entirely on Vulkan, which is not always allowable. ...
... RISC-V is a microprocessor which refers to "Reduced Instruction Set Computer Version Five". Its instruction set architecture (ISA) has been open and well known for its high performance since its appearance in 2011 up till now in addition to other properties like: Modular, Flexible, open-source tools and license [1][2]. ...
... Leaving aside the effects of diffraction scattering, the most appropriate solutions for computer simulation of the background illumination that occurs at the image sensor are radiation transfer methods based on stochastic ray tracing. 4 The simplest and most effective solutions are the methods of unidirectional (forward or backward) 1,5 ray tracing, which solve the radiation transfer equations or calculate the radiance using Monte Carlo integration methods, 6 based on algorithms for generating pseudorandom variables. Unidirectional Monte Carlo ray tracing methods are well known 7 and are a simple and reliable way of computer simulation of stray light propagation in an optical device and calculation of stray illumination in the image plane. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/854441464958983-1580726128113_Q64/Alexey-Voloboy.jpg)
... Respecto a la evolución del hardware, desde el punto de vista del render, en los últimos años han aparecido diferentes tarjetas gráficas que posibilitan la ejecución directamente sobre el hardware de algoritmos de iluminación realista en tiempo real (Sanzharov et al., 2020). Esta evolución es un cambio que aún está por llegar a los platós virtuales de televisión pero que cuando lo haga, unido a la mejora en los motores de render, supondrá un gran cambio en la calidad de los contenidos CGI incluidos en las producciones. ...
... Complete software implementations of OpenGL-style streaming pipelines, including sort-middle binning and hierarchical rasterization, have been presented for NVIDIA CUDA and OpenCL [Kenzel et al. 2018;Kim and Baek 2021]. A comprehensive analysis of previous software rasterization approaches and the challenges they tackle is found in [Frolov et al. 2020]. Most recently, software rasterization has received increased attention due to the launch of the Unreal Engine 5 and its virtual geometry feature, Nanite [Karis et al. 2021]. ...
... Since the emergence of the coordination service industry, there have been many problems such as loss of goods, noncompletion of goods, and dishonest transactions during coordination transportation. To increase the trust between each other, coordination service enterprises consume more resources when signing relevant agreements or contracts, which further increases the transaction costs and cannot improve the competitiveness of coordination service enterprises [4]. With the rapid development of the coordination service industry, people have put forward higher requirements for coordination service enterprises. ...
... Moreover, the PMC can compute the direct illumination, which is strongly not recommended in all kinds of the MLT. A drawback is the usually lower accuracy in the limit compared with the MLT [102]. ...
... Points are the basic elements of a graph [19]. In analytic geometry, points are represented by vectors [20,21]. For example, points in two-dimensional space (plane) and in three-dimensional space are separately represented by ...
... This pipelined architecture consists of vertex processing, geometry drawing, texturing, pixel operations, and frame buffer operations. Herein, OpenGL Secure Library (SC) is a subset of OpenGL commands that is described to develop safety-critical computer graphics such as DO-254 compatible multi-functional displays avionics platforms [5][6][7]. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/403219818795008-1473146504114_Q64/Vladimir-Kniaz.jpg)
... 2. Multiple-kernelcode is split into several smaller kernels, which communicate by reading/writing data into GPU memory. The necessity to read/write data from/into memory results in significant performance overhead depending on an application [51] 3. Wavefront path tracing. This approach extensively uses sorting and compaction of threads to organize them into several queues which execute different computational kernels. ...
Reference: An Auto-Programming Approach to Vulkan
