Mid-air images, which are augmented reality (AR) technologies, enable computer graphics (CG) images to be superimposed on a physical space. The mid-air image can be placed side-by-side with real objects, allowing vari...
详细信息
Mid-air images, which are augmented reality (AR) technologies, enable computer graphics (CG) images to be superimposed on a physical space. The mid-air image can be placed side-by-side with real objects, allowing various interactions, such as directly manipulating them to contact the mid-air image on the same plane. In this case, the measurement of the shape of real objects is necessary to realize geometric consistency between the mid-air image and real objects. However, in mid-air image optics, real objects cannot be placed behind the mid-air image (i.e., at a position where they interrupt the light rays that form the mid-air image). This limits the placement of the sensor and may prevent accurate measurement of the shape of the real objects. Consequently, we proposed an optical system for interaction with mid-air images that virtually measures the shape of real objects from behind the mid-air image. In our system, a virtual infrared (IR) sensor is formed behind the mid-air image using a hot mirror that reflects only IR light. The optical system considers the visible area of the mid-air image and the measurable area of the sensor. We evaluated the sharpness, luminance, and chromaticity to assess whether the hot mirror had changed the appearance of the mid-air image. The results confirmed that there was little impact on user perception. Furthermore, we developed four supporting applications for our system to show its efficacy.
Due to the evolution of graphics processors over recent decades it has now become possible to produce high-quality, realistic three-dimensional scenes. However, aliasing occurs during the sampling process performed du...
详细信息
Due to the evolution of graphics processors over recent decades it has now become possible to produce high-quality, realistic three-dimensional scenes. However, aliasing occurs during the sampling process performed during rasterization, which causes a serrated effect around the edges of the objects presented in the scene, highlighting an unreal aspect of the image and causing displeasure to the viewer. This paper aims to develop an anti-aliasing treatment based on rotated spatial filtering. It undertakes edge detection by applying spatial filtering with a simple linear regression technique. A smoothing spatial filter is then rotated to match the direction of the inspected edge and is applied to the affected regions. Testing was performed on an OpenGL application, processing the rendered image from the framebuffer, and Blender, a 3D modeling software that enables scenes with more complex graphics. The results have demonstrated the effectiveness of the proposed method in smoothing aliasing with good quality while preserving the details of the scene. Hence, the problem was managed effectively with a post-filtering approach and without oversampling. The running time of the algorithm is O(n), and the memory used is O(n).
The neural radiance field (NeRF) has shown promising results in preserving the fine details of objects and scenes. However, unlike explicit shape representations e.g., mesh, it remains an open problem to build dense c...
详细信息
The neural radiance field (NeRF) has shown promising results in preserving the fine details of objects and scenes. However, unlike explicit shape representations e.g., mesh, it remains an open problem to build dense correspondences across different NeRFs of the same category, which is essential in many downstream tasks. The main difficulties of this problem lie in the implicit nature of NeRF and the lack of ground-truth correspondence annotations. In this paper, we show it is possible to bypass these challenges by leveraging the rich semantics and structural priors encapsulated in a pre-trained NeRF-based GAN. Specifically, we exploit such priors from three aspects, namely (1) a dual deformation field that takes latent codes as global structural indicators, (2) a learning objective that regards generator features as geometric-aware local descriptors, and (3) a source of infinite object-specific NeRF samples. Our experiments demonstrate that such priors lead to 3D dense correspondence that is accurate, smooth, and robust. We also show that established dense correspondence across NeRFs can effectively enable many NeRF-based downstream applications such as texture transfer.
The authors propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real-time editing...
详细信息
The authors propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real-time editing. To achieve this, Gaussian Splatting Radiance Field is adopted as the scene representation and its explicit nature and speed advantage are fully leveraged. Its explicit representation formulation allows to devise a 2D prompt points to 3D masks dual-stage self-prompting segmentation algorithm, perform mask refinement and merging, minimize changes, and provide good initialization for scene inpainting and perform editing in real-time without per-editing training;all lead to superior quality and performance. The method was tested by editing both forward-facing and 360 scenes. The method is also compared against existing methods, showing superior quality despite being more capable and having a speed advantage. We propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here refers to intuitive object selection and real-time editing. This is achieved by devising a pipeline that fully exploits the explicit nature of our adopted scene representation. Our method achieves superior quality against existing object removal methods despite being more capable and having a speed advantage. image
Due to varied personal, social, or even cultural situations, people sometimes conceal or mask their true emotions. These suppressed emotions can be expressed in a very subtle way by brief movements called microexpress...
详细信息
Due to varied personal, social, or even cultural situations, people sometimes conceal or mask their true emotions. These suppressed emotions can be expressed in a very subtle way by brief movements called microexpressions. We investigate human subjects' perception of hidden emotions in virtual faces, inspired by recent psychological experiments. We created animations with virtual faces showing some facial expressions and inserted brief secondary expressions in some sequences, in order to try to convey a subtle second emotion in the character Our evaluation methodology consists of two sets of experiments, with three different sets of questions. The first experiment verifies that the accuracy and concordance of the participant's responses with synthetic faces matches the empirical results done with photos of real people in the paper by X.-b. Shen, Q. Wu, and X.-I. Fu, 2012, "Effects of the duration of expressions on the recognition of microexpressions," Journal of Zhejiang University Science 8, 13(3), 221-230. The second experiment verifies whether participants could perceive and identify primary and secondary emotions in virtual faces. The third experiment tries to evaluate the participant's perception of realism, deceit, and valence of the emotions. Our results show that most of the participants recognized the foreground (macro) emotion and most of the time they perceived the presence of the second (micro) emotion in the animations, although they did not identify it correctly in some samples. This experiment exposes the benefits of conveying microexpressions in computer graphics characters, as they may visually enhance a character's emotional depth through subliminal microexpression cues, and consequently increase the perceived social complexity and believability.
With the ongoing development of rendering technology, computer graphics (CG) are sometimes so photorealistic that to distinguish them from photographic (PG) images by human eyes has become difficult. To this end, many...
详细信息
With the ongoing development of rendering technology, computer graphics (CG) are sometimes so photorealistic that to distinguish them from photographic (PG) images by human eyes has become difficult. To this end, many methods have been developed for automatic CG and PG classification. In this paper, we present a simple, yet efficient, multiresolution approach to distinguish CG from PG based on uniform gray-scale invariant local binary patterns (LBPs) with the help of support vector machines (SVM). We select YCbCr as the color model. The original Joint Photographic Experts Group (JPEG) coefficients of Y, Cb, and Cr components and their prediction errors are used for two LBP operators. From each 2D array and each LBP operator, we obtain 59 uniform LBP features. In total, 12 groups of 59 features are obtained from each image. But after multiresolution analysis, we select six groups of 59 features for CG and PG classification. The proposed features have been tested with thousands of CG and PG. Classification accuracy reaches 95.1% with support vector machines and outperforms the state-of-the-art works. Copyright (c) 2013 John Wiley & Sons, Ltd.
In the field of scientific visualization, the upscaling of time-varying volume is meaningful. It can be used in in situ visualization to help scientists overcome the limitations of I/O speed and storage capacity when ...
详细信息
In the field of scientific visualization, the upscaling of time-varying volume is meaningful. It can be used in in situ visualization to help scientists overcome the limitations of I/O speed and storage capacity when analysing and visualizing large-scale, time-varying simulation data. This paper proposes self-attention residual network-based spatial super-resolution (SARN-SSR), a spatial super-resolution model based on self-attention residual networks that can generate time-varying data with temporal coherence. SARN-SSR consists of two components: a generator and a discriminator. The generator takes the low-resolution volume sequences as the input and gives the corresponding high-resolution volume sequences as the output. The discriminator takes both synthesized and real high-resolution volume sequence as the input and gives a matrix to predict the realness as the output. To verify the validity of SARN-SSR, four sets of time-varying volume datasets are applied from scientific simulation. In addition, SARN-SSR is compared on these datasets, both qualitatively and quantitatively, with two deep learning-based techniques and one traditional technique. The experimental results show that by using this method, the closest time-varying data to the ground truth can be obtained. This paper proposes a novel self-attention residual network-based spatial super-resolution (SARN-SSR) framework for upscaling time-varying volume data in scientific visualization. It utilizes a generator and discriminator based on generative adversarial networks to generate high-resolution volume sequences. Comparative evaluations demonstrate that SARN-SSR outperforms state-of-the-art techniques in generating accurate time-varying volume datasets. image
We present a novel approach for generating isotropic surface triangle meshes directly from unoriented 3D point clouds, with the mesh density adapting to the estimated local feature size (LFS). Popular reconstruction p...
详细信息
We present a novel approach for generating isotropic surface triangle meshes directly from unoriented 3D point clouds, with the mesh density adapting to the estimated local feature size (LFS). Popular reconstruction pipelines first reconstruct a dense mesh from the input point cloud and then apply remeshing to obtain an isotropic mesh. The sequential pipeline makes it hard to find a lower-density mesh while preserving more details. Instead, our approach reconstructs both an implicit function and an LFS-aware mesh sizing function directly from the input point cloud, which is then used to produce the final LFS-aware mesh without remeshing. We combine local curvature radius and shape diameter to estimate the LFS directly from the input point clouds. Additionally, we propose a new mesh solver to solve an implicit function whose zero level set delineates the surface without requiring normal orientation. The added value of our approach is generating isotropic meshes directly from 3D point clouds with an LFS-aware density, thus achieving a trade-off between geometric detail and mesh complexity. Our experiments also demonstrate the robustness of our method to noise, outliers, and missing data and can preserve sharp features for CAD point clouds.
The limited of texture details information in low-resolution facial or eye images presents a challenge for gaze estimation. To address this, FSKT-GE (feature maps similarity knowledge transfer for low-resolution gaze ...
详细信息
The limited of texture details information in low-resolution facial or eye images presents a challenge for gaze estimation. To address this, FSKT-GE (feature maps similarity knowledge transfer for low-resolution gaze estimation) is proposed, a gaze estimation framework consisting of both a high resolution (HR) network and low resolution (LR) network with the identical structure. Rather than mere feature imitation, this issue is addressed by assessing the cosine similarity of feature layers, emphasizing the distribution similarity between the HR and LR networks. This enables the LR network to acquire richer knowledge. This framework utilizes a combination loss function, incorporating cosine similarity measurement, soft loss based on probability distribution difference and gaze direction output, along with a hard loss from the LR network output layer. This approach on low-resolution datasets derived from Gaze360 and RT-Gene datasets is validated, demonstrating excellent performance in low-resolution gaze estimation. Evaluations on low-resolution images obtained through 2x, 4x, and 8x down-sampling are conducted on two datasets. On the Gaze360 dataset, the lowest mean angular errors of 10.97 degrees, 11.22 degrees, and 13.61 degrees were achieved, while on the RT-Gene dataset, the lowest mean angular errors of 6.73 degrees, 6.83 degrees, and 7.75 degrees were obtained. Here, a novel approach called feature map similarity-based knowledge transfer for low-resolution gaze estimation (FSKT-GE) is proposed. The motivation behind this work is to address the challenge of accurately estimating gaze direction for low-resolution facial images encountered in unconstrained outdoor environments. image
Electroencephalography (EEG) is a novel modality for investigating perceptual graphics problems. Until recently, EEG has predominantly been used for clinical diagnosis, in psychology, and by the brain-computer-interfa...
详细信息
Electroencephalography (EEG) is a novel modality for investigating perceptual graphics problems. Until recently, EEG has predominantly been used for clinical diagnosis, in psychology, and by the brain-computer-interface community. Researchers are extending it to help understand the perception of visual output from graphics applications and to create approaches based on direct neural feedback. Researchers have applied EEG to graphics to determine perceived image and video quality by detecting typical rendering artifacts, to evaluate visualization effectiveness by calculating the cognitive load, and to automatically optimize rendering parameters for images and videos on the basis of implicit neural feedback.
暂无评论