This article delves into the topic of essential tremor detection through the integration of software recording techniques with graphics tablets and the JPen library. Essential tremor, a common neurological disorder ch...
详细信息
Generating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to...
详细信息
Generating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to the existing human modeling techniques, our method does not require a statistical body shape model. We exploit Variational Autoencoders to develop a novel framework capable of transitioning from a simple 2D stick figure sketch, to a corresponding 3D human model. Our network learns the mapping between the input sketch and the output 3D model. Furthermore, our model learns the embedding space around these models. We demonstrate that our network can generate not only 3D models, but also 3D animations through interpolation and extrapolation in the learned embedding space. In addition to 3D human models, we produce 3D horse models in order to show the generalization ability of our framework. Extensive experiments show that our model learns to generate compatible 3D models and animations with 2D sketches. (C) 2022 The Author(s). Published by Elsevier Ltd.
We present a new approach for path finding in weighted graphs using pre-computed minimal distance fields. By selecting the most promising minimal distance field at any given node and switching between them, our algori...
详细信息
We present a new approach for path finding in weighted graphs using pre-computed minimal distance fields. By selecting the most promising minimal distance field at any given node and switching between them, our algorithm aims to find the shortest path possible. As we show, this approach scales excellently for various topologies, graph sizes and hardware specifications while maintaining a mean length error below 1% and reasonable memory consumption. By utilizing a simplified structure and keeping backtracking to a minimum, we are able to leverage the same approach on the massively parallel GPUs or any other shared memory parallel architecture, reducing the run time even further. (C) 2021 Elsevier Ltd. All rights reserved.
Deep learning for image processing typically treats input imagery as pixels in some color space. This paper proposes instead to learn from program traces of procedural fragment shaders - programs that generate images....
详细信息
Deep learning for image processing typically treats input imagery as pixels in some color space. This paper proposes instead to learn from program traces of procedural fragment shaders - programs that generate images. At each pixel, we collect the intermediate values computed at program execution, and these data form the input to the learned model. We investigate this learning task for a variety of applications: our model can learn to predict a low-noise output image from shader programs that exhibit sampling noise;this model can also learn from a simplified shader program that approximates the reference solution with less computation, as well as learn the output of postprocessing filters like defocus blur and edge-aware sharpening. Finally we show that the idea of learning from program traces can even be applied to non-imagery simulations of flocks of boids. Our experiments on a variety of shaders show quantitatively and qualitatively that models learned from program traces outperform baseline models learned from RGB color augmented with hand-picked shader-specific featues like normals, depth, and diffuse and specular color. We also conduct a series of analyses that show certain features within the trace are more important, and even learning from a small subset of the trace outperforms the baselines.
Image systems simulation software can accelerate innovation by reducing many of the time-consuming and expensive steps in designing, building, and evaluating image systems. To realize this potential, it is necessary t...
详细信息
Image systems simulation software can accelerate innovation by reducing many of the time-consuming and expensive steps in designing, building, and evaluating image systems. To realize this potential, it is necessary to build trust in physics-based end-to-end image systems simulations. Toward this goal, we describe and experimentally validate an end-to-end physics-based image systems simulation of a digital camera. The simulation models the spectral radiance of 3-D scenes, the formation of the spectral irradiance by multielement optics, and the conversion of the irradiance to digital values (DVs) by the image sensor. We quantify the accuracy of the simulation by comparing real and simulated images of a precisely constructed, 3-D high-dynamic range (HDR) test scene.
In recent years, there have been numerous initiatives regarding the incorporation of building performance simulation tools (BPSTs) in the field of architecture, but unfortunately they have not been considered in updat...
详细信息
In recent years, there have been numerous initiatives regarding the incorporation of building performance simulation tools (BPSTs) in the field of architecture, but unfortunately they have not been considered in updates of the curricula of building designers' careers at a global level. This paper presents an example of the use of BPSTs in the decision making of architectural models, after confirming that there is a lack of knowledge regarding these programs in architecture classrooms. As a result, based on the literature review, improvement aspects and recommendations have been identified and consequences for future research have been foreseen. To this end, the growing trend in the use of these tools has been analyzed, both in terms of the impact on architectural design and their use by architects. The authors' perceptions led us to confirm that the disconnection between BPSTs and architectural students can easily be diminished and alleviated through the teaching-learning process. We also noted the importance of energy modelling in the initial stages of architectural design. In addition, a proposed format for the application of BPSTs to architectural design for architects is presented.
Aiming at the problems of high damage rate of cultural relics, low processing efficiency and fuzzy detail processing when producing handmade rubbing, a method of generating digital rubbing of Han Dynasty Stone Relief ...
详细信息
Generative Adversarial Networks (GANs) have established themselves as a prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability ...
详细信息
Generative Adversarial Networks (GANs) have established themselves as a prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks. This state-of-the-art report covers the StyleGAN architecture, and the ways it has been employed since its conception, while also analyzing its severe limitations. It aims to be of use for both newcomers, who wish to get a grasp of the field, and for more experienced readers that might benefit from seeing current research trends and existing tools laid out. Among StyleGAN's most interesting aspects is its learned latent space. Despite being learned with no supervision, it is surprisingly well-behaved and remarkably disentangled. Combined with StyleGAN's visual quality, these properties gave rise to unparalleled editing capabilities. However, the control offered by StyleGAN is inherently limited to the generator's learned distribution, and can only be applied to images generated by StyleGAN itself. Seeking to bring StyleGAN's latent control to real-world scenarios, the study of GAN inversion and latent space embedding has quickly gained in popularity. Meanwhile, this same study has helped shed light on the inner workings and limitations of StyleGAN. We map out StyleGAN's impressive story through these investigations, and discuss the details that have made StyleGAN the go-to generator. We further elaborate on the visual priors StyleGAN constructs, and discuss their use in downstream discriminative tasks. Looking forward, we point out StyleGAN's limitations and speculate on current trends and promising directions for future research, such as task and target specific fine-tuning.
Spatial systems like shells, arches and shelters can often be used as temporary structures to accommodate short to medium expositions, events, or emergencies. This has historically allowed them to be designed for mult...
详细信息
Light leaking in Probe GI is typically solved by visibility tests, which cannot benefit from hardware-aided tri-linear sampling. We present Mask Decomposition, which decomposes the visibility into probe-group indicato...
详细信息
Light leaking in Probe GI is typically solved by visibility tests, which cannot benefit from hardware-aided tri-linear sampling. We present Mask Decomposition, which decomposes the visibility into probe-group indicators and their corresponding masks, making it possible to use tri-linear sampling in its reconstruction. We prove that the rendering overhead is significantly reduced with the help of Mask Decomposition, making the rendering at least 3 x faster than the state-of-the-art visibility-test Probe GI, and even as fast as the original leaking probe GI. We also present an efficient algorithm to solve the Mask Decomposition problem and a simple compression method to minimize the spatial overhead of the mask textures, which is much lower than in compression methods like Moving Basis Decomposition (MBD).
暂无评论