Showing papers on "Software rendering published in 2023"

Concurrent pipeline rendering scheme based on GPU multi-queue and partitioning images

Abstract: Compared with rasterization rendering, ray tracing rendering can improve the image’s visual effect and make the image look more realistic. Real-time ray tracing requires very high computing power of Graphics Processing Unit (GPU). When the number of GPUs is limited and the performance of a single GPU cannot be fully utilized, high rendering latency will occur. In this paper, we propose Multi-Queue Concurrent Pipeline Rendering (MQCPR), a novel ray-tracing parallel rendering scheme based on GPU multi-queue. This scheme divides the image area into multiple parts and uses multi-queue of GPU to enable the computation and transmission tasks in the rendering process to be executed simultaneously, which can maximize the performance of a single GPU and improve the graphics rendering speed. MQCPR may keep the GPU busy to make full use of the GPU resources. Experiments illustrate that in the case of a single GPU, compared with the single queue serial rendering scheme, the number of Frames Per Second (FPS) is increased by 1.5 times after using MQCPR.

Research on Energy Saving Control of 3D Animation Rendering Cluster Based on Programmable Processor

Abstract: Cluster rendering is very necessary in today’s 3D animation rendering and HD post video production. From the initial processing of a single still image to the current rendering of video and 3D scene, from the original rendering process requires a lot of manual interaction to the current computer automatic recognition and rendering. Due to the support of programmable graphics hardware, many rendering technologies can render video or 3D scene in real time and become animation after improvement and acceleration. One of the biggest problems in stylized line drawing of 3D models is the calculation of visibility. In the current algorithm for calculating line visibility with complex models, either the interactive rendering speed is too slow or the rendered animation is incoherent. An algorithm for fast, high-quality calculation of line visibility under the GPU, which utilizes advanced programmable graphics pipeline technology that supports line visibility and a wide range of stylization options. This paper studies the energy consumption of rendering clusters in the field of 3D animation rendering, adopts the task volume prediction model based on neural network, and combines the historical data statistics of rendering system task volume, and proposes a multi-step prediction-based rendering cluster automatic on-off control algorithm and energy-saving control architecture. And the effectiveness of the energy-saving control method is verified by actual data.

Evaluation and Optimization of Rendering Techniques for Autonomous Driving Simulation

Abstract: In order to meet the demand for higher scene rendering quality from some autonomous driving teams (such as those focused on CV), we have decided to use an offline simulation industrial rendering framework instead of real-time rendering in our autonomous driving simulator. Our plan is to generate lower-quality scenes using a game engine, extract them, and then use an IQA algorithm to validate the improvement in scene quality achieved through offline rendering. The improved scenes will then be used for training.

NeRFahedron

Abstract: Neural rendering is an exciting topic injecting machine learning methodologies into the classical computer graphics rendering pipeline. Although recent works have achieved remarkable fidelity, discussion on how to enable it for interactive scenarios like video games seems to be lacking. Aside from an editable 3D model and UV-mapping, an interactive application will demand the neural rendering to handle animatable 3D content with interactive speed. This is currently a gap in neural rendering and our solution to this problem is a novel neural rendering pipeline involving a primitive named NeRFahedron. It localizes a NeRF field and as such effectively reduces the number of expensive network sampling operations to improve speed. Our pipeline involves tetrahedron rasterization, localized ray marching and near-surface particle sampling. The result is a method that can enable animatable content for neural rendering with interactive speed, which has been shown to be competitive in rendering animation. We will also showcase its ability to enable interactive applications via a real-time demo.

Hardware Acceleration of Neural Graphics

Abstract: Rendering and inverse rendering techniques have recently attained powerful new capabilities and building blocks in the form of neural representations (NR), with derived rendering techniques quickly becoming indispensable tools next to classic computer graphics algorithms, covering a wide range of functions throughout the full pipeline from sensing to pixels. NRs have recently been used to directly learn the geometric and appearance properties of scenes that were previously hard to capture, and to re-synthesize photo realistic imagery based on this information, thereby promising simplifications and replacements for several complex traditional computer graphics problems and algorithms with scalable quality and predictable performance. In this work we ask the question: Does neural graphics (graphics based on NRs) need hardware support? We studied four representative neural graphics applications (NeRF, NSDF, NVR, and GIA) showing that, if we want to render 4k resolution frames at 60 frames per second (FPS) there is a gap of ~ 1.51× to 55.50× in the desired performance on current GPUs. For AR and VR applications, there is an even larger gap of ~ 2--4 orders of magnitude (OOM) between the desired performance and the required system power. We identify that the input encoding and the multi-layer perceptron kernels are the performance bottlenecks, consuming 72.37%, 60.0% and 59.96% of application time for multi resolution hashgrid encoding, multi resolution densegrid encoding and low resolution densegrid encoding, respectively. We propose a neural graphics processing cluster (NGPC) - a scalable and flexible hardware architecture that directly accelerates the input encoding and multi-layer perceptron kernels through dedicated engines and supports a wide range of neural graphics applications. To achieve good overall application level performance improvements, we also accelerate the rest of the kernels by fusion into a single kernel, leading to a ~ 9.94× speedup compared to previous optimized implementations [17] which is sufficient to remove this performance bottleneck. Our results show that, NGPC gives up to 58.36× end-to-end application-level performance improvement, for multi resolution hashgrid encoding on average across the four neural graphics applications, the performance benefits are 12.94×, 20.85×, 33.73× and 39.04× for the hardware scaling factor of 8, 16, 32 and 64, respectively. Our results show that with multi resolution hashgrid encoding, NGPC enables the rendering of 4k Ultra HD resolution frames at 30 FPS for NeRF and 8k Ultra HD resolution frames at 120 FPS for all our other neural graphics applications.

Direct Rendering of Three-Dimensional Objects Based on Perturbation Functions Using GPUs

Abstract: The object of the study is a method of direct rendering of complex three-dimensional objects based on perturbation functions using graphics processors, using a variety of streaming multiprocessors. Direct rendering means that the visualization of functionally defined models takes place without their preliminary conversion to other formats, for example, into triangle grids. The research method is based on analytical geometry in space, differential geometry, interpolation theory and matrix theory, based on mathematical modeling and the theory of computing systems. The main conclusions of the study are: the possibility of direct rendering of functionally specified objects, when rendering it is important that the computing processors are not idle. The first problem that was solved was that different GPUs have different numbers of streaming multiprocessors. Therefore, it was necessary to choose during execution the optimal stage from which the work began. Thus, you can partially get rid of the problem with unused computing resources. The second problem, the balancing problem, was solved by using a large number of computing processors. For implementation, the CUDA parallel programming model was used, which, together with a set of software tools, allows implementing programs in the C language for execution on a GPU. The resulting system visualizes complex functionally defined objects with high resolution interactively. The dependence of performance on the computing power of graphics processors is investigated.

Post0-VR: Enabling Universal Realistic Rendering for Modern VR via Exploiting Architectural Similarity and Data Sharing

Abstract: To provide users with a fully immersive environment, VR post-processing, which adds numerous realistic effects on the frame after rendering, plays a key role in modern VR systems. Current post-processing is processed separately from normal rendering by the graphics processing unit (GPU). As a result, the GPU needs to first render a high-resolution frame and then add the post-processing effects within a very short time frame. Our in-depth experimental results on commercial VR products demonstrate that the post-processing in VR applications extends the VR frame time by approximately 2X on average. Furthermore, the ever-increasing resolution requirements of modern VR significantly increase the workloads for post-processing in the execution pipeline. This long delay causes VR real-time execution to frequently miss the critical frame-time deadline, thus hurting users’ quality of experience.Based on the analysis of VR post-processing workflow and its common realistic effects, we observe that post-processing shares the same hardware pipeline with normal rendering, and even reuses the intermediate data produced by normal rendering. To fully utilize this hardware-level similarity and capture the data locality, we propose a novel universal realistic rendering architecture for VR, named Post0-VR, which eliminates post-processing by directly merging the common realistic effects into the normal rendering process. Based on our newly proposed VR architecture design, we further propose a dynamic accuracy adjustment method to simplify the normal rendering without hurting users’ perception. The evaluation results on real-world applications demonstrate that Post0-VR can support different types of realistic effects while significantly improving the overall VR rendering performance.

NeRFahedron: A Primitive for Animatable Neural Rendering with Interactive Speed

Abstract: pipeline

Research on 3D Rendering Effect under Multi-strategy

Abstract: With the development of computer hardware and rendering methods, efficient and high-quality 3D rendering strategies have become the focus of current research. This paper takes hardware configuration and rendering methods as variables to explore the rendering effects of materials, textures, lights, a

Hardware Acceleration of Neural Graphics

Abstract: Rendering and inverse-rendering algorithms that drive conventional computer graphics have recently been superseded by neural representations (NR). NRs have recently been used to learn the geometric and the material properties of the scenes and use the information to synthesize photorealistic imagery, thereby promising a replacement for traditional rendering algorithms with scalable quality and predictable performance. In this work we ask the question: Does neural graphics (NG) need hardware support? We studied representative NG applications showing that, if we want to render 4k res. at 60FPS there is a gap of 1.5X-55X in the desired performance on current GPUs. For AR/VR applications, there is an even larger gap of 2-4 OOM between the desired performance and the required system power. We identify that the input encoding and the MLP kernels are the performance bottlenecks, consuming 72%,60% and 59% of application time for multi res. hashgrid, multi res. densegrid and low res. densegrid encodings, respectively. We propose a NG processing cluster, a scalable and flexible hardware architecture that directly accelerates the input encoding and MLP kernels through dedicated engines and supports a wide range of NG applications. We also accelerate the rest of the kernels by fusing them together in Vulkan, which leads to 9.94X kernel-level performance improvement compared to un-fused implementation of the pre-processing and the post-processing kernels. Our results show that, NGPC gives up to 58X end-to-end application-level performance improvement, for multi res. hashgrid encoding on average across the four NG applications, the performance benefits are 12X,20X,33X and 39X for the scaling factor of 8,16,32 and 64, respectively. Our results show that with multi res. hashgrid encoding, NGPC enables the rendering of 4k res. at 30FPS for NeRF and 8k res. at 120FPS for all our other NG applications.

Application and study of virtual reality in the diagnosis system of peritoneal effusion

Abstract: The virtual reality-based pneumoperitoneum diagnosis system is an important part of the simulation of laparotomy, and the simulation of pneumoperitoneum is the key to virtual puncture teaching. This paper conducts a test study on the frame rate, the rendering time per frame, the number of triangles and fixed points to be drawn and other related factors during the simulation of pneumoperitoneum. The paper compares the topographic water resources in the standard repository provided by unity and the water resources in the OBI particle system, and addresses the problems and shortcomings of the topographic water in the standard repository, which cannot flow due to gravity and has poor simulation quality, and the OBI particle system, which has low rendering frame rate and long rendering time for simulating water, and proposes a Shader Graph water rendering method based on the Shader Graph, and then simulates the peritoneal fluid through programming, improved rendering frame rate, reduced the number of unnecessary drawn triangles and vertices, and accelerated rendering time.

Locomotion-aware Foveated Rendering

Abstract: Optimizing rendering performance improves the user's immersion in virtual scene exploration. Foveated rendering uses the features of the human visual system (HVS) to improve rendering performance without sacrificing perceptual visual quality. We collect and analyze the viewing motion of different locomotion methods, and describe the effects of these viewing motions on HVS's sensitivity, as well as the advantages of these effects that may bring to foveated rendering. Then we propose the locomotion-aware foveated rendering method (LaFR) to further accelerate foveated rendering by leveraging the advantages. In LaFR, we first introduce the framework of LaFR. Secondly, we propose an eccentricity-based shading rate controller that provides the shading rate control of the given region in foveated rendering. Thirdly, we propose a locomotion-aware log-polar mapping method, which controls the foveal average shading rate, the peripheral shading rate decrease speed, and the overall shading quantity with the locomotion-aware coefficients based on the eccentricity-based shading rate controller. LaFR achieves similar perceptual visual quality as the conventional foveated rendering while achieving up to 1.6× speedup. Compared with the full resolution rendering, LaFR achieves up to 3.8× speedup.

FoVolNet: Fast Volume Rendering using Foveated Deep Neural Networks

Abstract: Volume data is found in many important scientific and engineering applications. Rendering this data for visualization at high quality and interactive rates for demanding applications such as virtual reality is still not easily achievable even using professional-grade hardware. We introduce FoVolNet-a method to significantly increase the performance of volume data visualization. We develop a cost-effective foveated rendering pipeline that sparsely samples a volume around a focal point and reconstructs the full-frame using a deep neural network. Foveated rendering is a technique that prioritizes rendering computations around the user's focal point. This approach leverages properties of the human visual system, thereby saving computational resources when rendering data in the periphery of the user's field of vision. Our reconstruction network combines direct and kernel prediction methods to produce fast, stable, and perceptually convincing output. With a slim design and the use of quantization, our method outperforms state-of-the-art neural reconstruction techniques in both end-to-end frame times and visual quality. We conduct extensive evaluations of the system's rendering performance, inference speed, and perceptual properties, and we provide comparisons to competing neural image reconstruction techniques. Our test results show that FoVolNet consistently achieves significant time saving over conventional rendering while preserving perceptual quality.

Product Feature Modeling Based on Graphics and Image Fusion

Abstract: With the development of graphics and image fusion technology, product feature modeling has become an important part of people’s improvement of quality of life. This paper combines image-based rendering techniques and geometry-based rendering techniques to describe indoor virtual scenes. Since the virtual indoor space can only be used to describe a part of the indoor environment, and in order to improve the interactivity of the virtual scene, the system provides an import function of the physical model. Finally, this paper introduces the concept of time into the system, providing two methods of real-time rendering and non-real-time rendering to handle different rendering requirements, providing animation and interactive roaming to make it have the characteristics of virtual environment. The system approximates the monitoring environment by simple modeling, multiple mapping methods and importing models, and has strong practicability, good real-time performance and display effect.

Introduction

Abstract: Computer graphics is the process of creating images using a computer. This process is often referred to as graphic data processing. In this book, an image is understood in an abstract sense. An image can represent a realistic scene from the everyday world, but it can also be graphics such as histograms or pie charts, or the graphical user interface of the software. This chapter presents examples of some application areas of computer graphics to give an impression of the broad spectrum of tasks in this discipline. This is followed by explanations of the main steps in computer graphics and an overview of how a rendering pipeline works using the graphics pipeline of the Open Graphics Library (OpenGL). This basic mode of operation can be transferred to other graphics systems.

Accelerating path tracing rendering with Multi-GPU in Blender cycles

Abstract: Metaverse is one of the current hottest research fields, which not only requires rendering techniques such as path tracing but also rendering engines such as Blender. However, rendering scenes by path tracing is a complex and computationally intensive process, especially for large scenes, causing catastrophically slow rendering using only a single GPU.To improve rendering performance, we use multiple GPUs to achieve parallel rendering in Blender Cycles for path tracing. First, we distribute the workload based on pixel blocks. Each GPU renders one of the image fragments to finally combine the rendering results into a complete image. Second, we propose a Dynamic Workload Adjustment Algorithm (DWAA) to solve the workload imbalance problem. DWAA takes advantage of the fact that path tracing requires multiple samples, so it increases or decreases the work area of each GPU for the next ray sample according to the rendering time of each GPU’s last path-tracing sample, which can reduce GPU idle time and improve overall rendering performance.To evaluate the Multi-GPUs rendering approach and DWAA, we use two different scale scenes - Babershop and Junkshop, and test them with different GPU clusters consisting of 2, 3, and 4 NVIDIA A100 GPUs respectively. The results show that compared to a single GPU, 2 GPUs can accelerate up to 1.98x, 3 GPUs up to 2.94x, and 4 GPUs up to 3.9x, which has high scalability and the parallelism is close to linear increase.