Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry最新文献_第3页

A Novel Clustering-Based Image Inpainting Model Using the Loermgan Algorithm 一种新的基于Loermgan算法的聚类图像绘制模型

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574440

Ishan Sharma, Yongwei Nie

{"title":"A Novel Clustering-Based Image Inpainting Model Using the Loermgan Algorithm","authors":"Ishan Sharma, Yongwei Nie","doi":"10.1145/3574131.3574440","DOIUrl":"https://doi.org/10.1145/3574131.3574440","url":null,"abstract":"The process of recovering the damaged or missing areas from an image utilizing information as of known portions is termed Image Inpainting. To refurbish the damaged image into a new one alike an actual image, numerous sophisticated methodologies have been established to date. Nevertheless, in the case of images with a larger missing region, these models are not effective in addressing the problem. Likewise, these methodologies are ineffective towards the edge. Therefore, by utilizing the Log of Exponent Rule Generative Adversarial Network algorithm, a novel clustering-centric image inpainting system has been proposed here. Initially, two significant steps, namely (i) noise removal, and (ii) Contrast Enhancement (CE), are performed to pre-process the input images. After that, by utilizing the Adaptive Max One-Sided Box Filter (AMOSBF) algorithm, the pre-processed images’ edges are well-preserved. Then, the most needed features are extracted as of the edge preserved images. Next, by employing Supremum Distance Fast Density Peaks Clustering Algorithm (SDFDPCA), the features being extracted are clustered. Next, the proposed model, termed Log of Exponent Rule Mish Generative Adversarial Network (LOERMGAN), which reconstructs the actual images effectively, is fed with the clustered features and also the masked image and the mask itself. In this research, the openly accessible datasets termed ADE20k, Paris, and Places2 are utilized. Subsequently, the outcomes obtained are analogized with the prevailing methodologies. The experiential outcomes displayed that the proposed model outshines the other prevailing methodologies by effectively reconstructing images.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116132123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised Embroidery Generation Using Embroidery Channel Attention 使用刺绣频道注意力的无监督刺绣生成

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574430

Chen Yang, Xinrong Hu, Yangjun Ou, Saishang Zhong, Tao Peng, Lei Zhu, P. Li, Bin Sheng

{"title":"Unsupervised Embroidery Generation Using Embroidery Channel Attention","authors":"Chen Yang, Xinrong Hu, Yangjun Ou, Saishang Zhong, Tao Peng, Lei Zhu, P. Li, Bin Sheng","doi":"10.1145/3574131.3574430","DOIUrl":"https://doi.org/10.1145/3574131.3574430","url":null,"abstract":"It is a challenging task to synthesize an embroidery image with complex texture from a colorful image. Existing style transfer methods to synthesize embroidery images will lead to color shift and texture clutter. In this paper, the generative adversarial network architecture with embroidery channel attention is proposed to synthesize embroidery images based on the unaligned dataset. Our method can synthesize the color and texture images generated separately from the features of the input image without extra data and cycle network. The generator with embroidery channel attention in our network can generate three attention masks (texture attention mask, color attention mask, original attention mask) and two content masks (color content mask and texture content mask). The color image and texture image of embroidery are synthesized separately with these masks. Meanwhile, a color loss function is proposed to encourage the color of the generated image to be close to that of the original image. In addition, a white padding processing technology is proposed to improve the stability of global embroidery texture synthesis. Existing extensive experiments show that our method synthesizes the embroidery images with realistic color and stable texture to solve the color shift and texture clutter. In the case of ensuring the content of the input images, the results synthesized by our method are closer to the real embroidery.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129076717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computer-vision Classification-algorithms Are Inherently Creative When Error-prone 计算机视觉分类算法在容易出错时具有固有的创造性

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574444

J. Hoorn

{"title":"Computer-vision Classification-algorithms Are Inherently Creative When Error-prone","authors":"J. Hoorn","doi":"10.1145/3574131.3574444","DOIUrl":"https://doi.org/10.1145/3574131.3574444","url":null,"abstract":"Whether coming from a linear support vector machine, from logistic regression, or a quasi-Newtonian, the fine-tuning of the decision boundary in any given data set is essential to mitigate the loss term so that neural nets in image recognition can divide a data space into separate sections and correctly classify an input. By their very nature, neural nets are logically non-deterministic but rest on probability-weighted associations, which are adjusted recursively to enhance the similarity of intermediate results to the target output, the remaining difference being the ‘error.’ However, taxonomies should not be crisp but seen as fuzzy classes, allowing for hybrid exemplars that transgress category boundaries. The associative and similarity orientation of neural nets and deep learning makes such systems inherently creative in that misclassifications are at the basis of creative crossovers in information processing. This new conceptualization of network errors is supported by the ratings of 40 top-ranking designers of 20 image-recognition mistakes on the dimensions of creativity and innovativeness.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115476497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

6-DoF Pose Relocalization for Event Cameras With Entropy Frame and Attention Networks 基于熵帧和注意网络的事件相机六自由度姿态重定位

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574457

Hu Lin, Meng Li, Qianchen Xia, Yifeng Fei, Baocai Yin, Xin Yang

{"title":"6-DoF Pose Relocalization for Event Cameras With Entropy Frame and Attention Networks","authors":"Hu Lin, Meng Li, Qianchen Xia, Yifeng Fei, Baocai Yin, Xin Yang","doi":"10.1145/3574131.3574457","DOIUrl":"https://doi.org/10.1145/3574131.3574457","url":null,"abstract":"Camera relocalization is an important task in computer vision, mainly used in applications such as VR, AR, and robotics. Camera relocalization solves the problem of estimating the 6-DoF camera pose of an input image in a known scene. There are large numbers of research on standard cameras. However, standard cameras have problems such as large power consumption, low frame rate, and poor robustness. Event cameras can make up for the disadvantages of standard cameras. Event data is different from RGB data, it is asynchronous streaming data, most of the processing methods for events convert event data into event images, but these methods can not efficiently generate event images with clear edges at any time, we propose a Reversed Window Entropy Image (RWEI) generation framework for events, which can generate event images with clear edges at any time. We also propose an Attention-guided Event Camera Relocalization Network (AECRN) for utilizing event image characteristics to estimate the pose of the event camera more accurately. We demonstrate our proposed framework and network on public dataset sequences, and experiments show that our proposed method surpasses the previous method.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125216980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Anomaly Detection and Localization via Simulated Anomalies 基于模拟异常的鲁棒异常检测与定位

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574463

Yadang Chen, Mei Wang, Duolin Wang, Dichao Li

{"title":"Robust Anomaly Detection and Localization via Simulated Anomalies","authors":"Yadang Chen, Mei Wang, Duolin Wang, Dichao Li","doi":"10.1145/3574131.3574463","DOIUrl":"https://doi.org/10.1145/3574131.3574463","url":null,"abstract":"Anomaly detection refers to identifying abnormal images and localizing anomalous regions. Reconstruction-based anomaly detection is a commonly used method; however, traditional reconstruction-based methods perform poorly as deep models generalize successfully enough that even anomalous regions can be well-restored. In this paper, we propose a new method to address the single pseudo-anomaly type and high false positive detection of the existing methods. Specifically, we design a novel pseudo-anomaly simulation module that can generate several types of anomalies on normal images. Furthermore, we propose an effective reconstruction network to improve the robustness of the model against distractors. Finally, we employ a segmentation network to localize anomalous regions. This simple but effective method can detect various anomalies in the real world, even those that are subtle and rare. Extensive experiments on the MVTec anomaly detection dataset demonstrate the effectiveness and superiority of the proposed method, yielding an AUROC score of 98.2% in image-level anomaly detection and 97.8% in pixel-level anomaly localization.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130445405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bridging Curatorial Intent and Visiting Experience: Using AR Guidance as a Storytelling Tool 连接策展意图和参观体验:使用AR引导作为讲故事的工具

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574438

Ze-Feng Gao, Anqi Wang, Pan Hui, Tristan Braud

{"title":"Bridging Curatorial Intent and Visiting Experience: Using AR Guidance as a Storytelling Tool","authors":"Ze-Feng Gao, Anqi Wang, Pan Hui, Tristan Braud","doi":"10.1145/3574131.3574438","DOIUrl":"https://doi.org/10.1145/3574131.3574438","url":null,"abstract":"Augmented Reality (AR) visits enhances the art exhibition experience by overlaying digital content. Although there has been significant interest in AR guides, few works leverage AR to bridge curatorial intent and audiences understanding. This paper focuses on integrating the curatorial intent within the AR overlays by developing the narrative layers established by the relationships between works. We develop a narrative system that identifies and links the primary art pieces of the exhibition within a digital story consistent with the curator’s perspective. The system is applied to a physical exhibition composed of seven art pieces. We evaluate the impact of AR overlays through two user experiments, conducted on art professionals and general audience, respectively. Both groups considered that the AR tour system improved interactivity, self-reported learning, and user satisfaction significantly (> 4/5). Besides, visitors found the system easy to get to do what they want to (4.7/5), and would use it for future visits (4.6/5). This study raises essential design considerations towards designing integrated AR museum guides that combine the perspective of artists and curators towards a better visiting experience.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132107977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

EHA-Transformer: Efficient and Haze-Adaptive Transformer for Single Image Dehazing eha变压器:用于单幅图像去雾的高效自适应变压器

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574429

Yu Zhou, Zhihua Chen, Ran Li, Bin Sheng, Lei Zhu, P. Li

{"title":"EHA-Transformer: Efficient and Haze-Adaptive Transformer for Single Image Dehazing","authors":"Yu Zhou, Zhihua Chen, Ran Li, Bin Sheng, Lei Zhu, P. Li","doi":"10.1145/3574131.3574429","DOIUrl":"https://doi.org/10.1145/3574131.3574429","url":null,"abstract":"Deep learning based dehazing structures have achieved significant progress in image haze removal. However, most recent methods mainly focused on the excellent feature extraction and representation capabilities of deep networks, and neglected the contributions of traditional haze-relevant priors to image dehazing. In this paper, we propose a novel dehazing method, named EHA-Transformer, which fully integrates the Transformer with haze-relevant features and enhances the interpretability. Since the haze distributions vary in different regions, the difficulties of local patch dehazing are also different. Based on this, we first propose a haze detector to distinguish regions, which are prone to produce residual haze during dehazing. Then, we introduce a haze-adaptive loss into our dehazing framework to increase the stability of the training process. Our dehazing framework is simple and generic, and can be easily applied to current dehazing models without introducing complexity. Since our EHA-Transformer takes full account of haze related properties, comprehensive experiments compared with state-of-the-arts demonstrate our framework have significant improvements in terms of robustness. We also apply our framework into different backbones, the noticeable improvements of different dehazing backbones illustrate the generalization capability of our framework.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127889583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Eye Tracking Emotion Evoking Interaction Based on Go/No-Go Paradigm VR Demonstration 基于Go/No-Go范式VR演示的眼动追踪情感激发交互

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574465

Feng Liu, Junhao Qin, Zhenying Zhang, Kecheng Tang, Jing Hu, Yihao Zhou

引用次数: 0

Touch Trick the mind: Haptic Display Augmented the Mind-Map of internal locus of control 触觉欺骗大脑:触觉显示增强了内部控制点的思维导图

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574449

Yuze Shen, Zhigeng Pan

{"title":"Touch Trick the mind: Haptic Display Augmented the Mind-Map of internal locus of control","authors":"Yuze Shen, Zhigeng Pan","doi":"10.1145/3574131.3574449","DOIUrl":"https://doi.org/10.1145/3574131.3574449","url":null,"abstract":"Previous work in VR has demonstrated that the haptic remapped technique uses visual domination of proprioceptive position sense to map virtual hand positions to match the internal locus of control. However, when the offset between virtual and physical hands gradually increases, the internal locus of control has difficulty in self-attributing the virtual hand movement, and the user becomes aware of the remapping process. Hence, we hypothesize that haptics can influence spatial perception by affecting the internal locus of control in a way that confuses the remapping process. In this paper, we present an experiment to evaluate performance in different cognitive environments to verify that haptics enhances people's perception of space by confusing the original threshold of vision to create illusions. And a haptic redirection is proposed to verify the effect of haptics on internal position control. We designed two experiments to estimate the perception of haptics for internal position sense. Our results quantitatively show that haptics can indeed reduce people's perceptual thresholds for spatial distance as well as depth in a way that alters internal perception by increasing illusion, and that a haptic-visual coherent environment can make the remapping of mismatches between virtual and physical locations less obvious.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116300951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Monocular Human Body Shape Estimation: A Generation-aid Approach 单目人体形状估计:一种辅助生成方法

Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry Pub Date : 2022-12-27 DOI: 10.1145/3574131.3574448

Lanfeng Zhou, Xiao-Shan Ji, Ling Li

{"title":"Monocular Human Body Shape Estimation: A Generation-aid Approach","authors":"Lanfeng Zhou, Xiao-Shan Ji, Ling Li","doi":"10.1145/3574131.3574448","DOIUrl":"https://doi.org/10.1145/3574131.3574448","url":null,"abstract":"Observing human beings from monocular images is one of the basic tasks of computer vision. Reconstructing human bodies from monocular images mainly includes the reconstruction of posture and body shape. However, in the past studies, researchers were more interested in pose estimation, ignoring the study of body shape, and this paper focuses on the estimation of the body shape of a 3D model. Learning body parameters via instance segmentation requires a large number of labels. While the parameters based on pose estimation are completely based on the results of key points detection, which effect is not friendly for pictures with poor angles and low resolution. In response to the above problems, we propose a method to automatically generate datasets. The dataset provides low-resolution images and labels of various angles and blurred shapes. On the generated low-resolution and poorly angled dataset, we propose a generative-assisted deep learning network framework. Experiments show that the framework can effectively estimate the body shape parameters of the model from monocular images.","PeriodicalId":111802,"journal":{"name":"Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114462568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0