Computational Visual Media最新文献_第4页

Multi3D: 3D-aware multimodal image synthesis Multi3D：三维感知多模态图像合成

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-04-03 DOI: 10.1007/s41095-024-0422-4

引用次数: 0

Active self-training for weakly supervised 3D scene semantic segmentation 弱监督三维场景语义分割的主动自我训练

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-03-22 DOI: 10.1007/s41095-022-0311-7

Gengxin Liu, Oliver van Kaick, Hui Huang, Ruizhen Hu

引用次数: 0

Class-conditional domain adaptation for semantic segmentation 用于语义分割的类条件域适应

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-03-22 DOI: 10.1007/s41095-023-0362-4

Yue Wang, Yuke Li, James H. Elder, Runmin Wu, Huchuan Lu

{"title":"Class-conditional domain adaptation for semantic segmentation","authors":"Yue Wang, Yuke Li, James H. Elder, Runmin Wu, Huchuan Lu","doi":"10.1007/s41095-023-0362-4","DOIUrl":"https://doi.org/10.1007/s41095-023-0362-4","url":null,"abstract":"Semantic segmentation is an important sub-task for many applications. However, pixel-level ground-truth labeling is costly, and there is a tendency to overfit to training data, thereby limiting the generalization ability. Unsupervised domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain (including less expensive synthetic domain) to be adapted to a novel target domain. The conventional approach involves automatic extraction and alignment of the representations of source and target domains globally. One limitation of this approach is that it tends to neglect the differences between classes: representations of certain classes can be more easily extracted and aligned between the source and target domains than others, limiting the adaptation over all classes. Here, we address this problem by introducing a Class-Conditional Domain Adaptation (CCDA) method. This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate that the performance of our CCDA method matches, and in some cases, surpasses that of state-of-the-art methods.\u0000","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140203925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Geometry-aware 3D pose transfer using transformer autoencoder 利用变换器自动编码器实现几何感知三维姿态转移

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-03-22 DOI: 10.1007/s41095-023-0379-8

Shanghuan Liu, Shaoyan Gai, Feipeng Da, Fazal Waris

{"title":"Geometry-aware 3D pose transfer using transformer autoencoder","authors":"Shanghuan Liu, Shaoyan Gai, Feipeng Da, Fazal Waris","doi":"10.1007/s41095-023-0379-8","DOIUrl":"https://doi.org/10.1007/s41095-023-0379-8","url":null,"abstract":"3D pose transfer over unorganized point clouds is a challenging generation task, which transfers a source’s pose to a target shape and keeps the target’s identity. Recent deep models have learned deformations and used the target’s identity as a style to modulate the combined features of two shapes or the aligned vertices of the source shape. However, all operations in these models are point-wise and independent and ignore the geometric information on the surface and structure of the input shapes. This disadvantage severely limits the generation and generalization capabilities. In this study, we propose a geometry-aware method based on a novel transformer autoencoder to solve this problem. An efficient self-attention mechanism, that is, cross-covariance attention, was utilized across our framework to perceive the correlations between points at different distances. Specifically, the transformer encoder extracts the target shape’s local geometry details for identity attributes and the source shape’s global geometry structure for pose information. Our transformer decoder efficiently learns deformations and recovers identity properties by fusing and decoding the extracted features in a geometry attentional manner, which does not require corresponding information or modulation steps. The experiments demonstrated that the geometry-aware method achieved state-of-the-art performance in a 3D pose transfer task. The implementation code and data are available at https://github.com/SEULSH/Geometry-Aware-3D-Pose-Transfer-Using-Transformer-Autoencoder.\u0000","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140203930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale hash encoding based neural geometry representation 基于神经几何表示的多尺度哈希编码

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-03-22 DOI: 10.1007/s41095-023-0340-x

{"title":"Multi-scale hash encoding based neural geometry representation","authors":"","doi":"10.1007/s41095-023-0340-x","DOIUrl":"https://doi.org/10.1007/s41095-023-0340-x","url":null,"abstract":"<h3>Abstract</h3> Recently, neural implicit function-based representation has attracted more and more attention, and has been widely used to represent surfaces using differentiable neural networks. However, surface reconstruction from point clouds or multi-view images using existing neural geometry representations still suffer from slow computation and poor accuracy. To alleviate these issues, we propose a multi-scale hash encoding-based neural geometry representation which effectively and efficiently represents the surface as a signed distance field. Our novel neural network structure carefully combines low-frequency Fourier position encoding with multi-scale hash encoding. The initialization of the geometry network and geometry features of the rendering module are accordingly redesigned. Our experiments demonstrate that the proposed representation is at least 10 times faster for reconstructing point clouds with millions of points. It also significantly improves speed and accuracy of multi-view reconstruction. Our code and models are available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction. <img alt=\"\" src=\"https://static-content.springer.com/image/MediaObjects/41095_2023_340_Fig1_HTML.jpg\"/> ","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140204009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Erratum to: Dynamic ocean inverse modeling based on differentiable rendering 勘误：基于可变渲染的动态海洋逆建模

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-03-22 DOI: 10.1007/s41095-024-0398-z

Xueguang Xie, Yang Gao, Fei Hou, Aimin Hao, Hong Qin

引用次数: 0

Delving into high-quality SVBRDF acquisition: A new setup and method 深入研究高质量 SVBRDF 采集：新的设置和方法

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-02-09 DOI: 10.1007/s41095-023-0352-6

Chuhua Xian, Jiaxin Li, Hao Wu, Zisen Lin, Guiqing Li

引用次数: 0

CF-DAN: Facial-expression recognition based on cross-fusion dual-attention network CF-DAN：基于交叉融合双注意网络的面部表情识别

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-02-08 DOI: 10.1007/s41095-023-0369-x

{"title":"CF-DAN: Facial-expression recognition based on cross-fusion dual-attention network","authors":"","doi":"10.1007/s41095-023-0369-x","DOIUrl":"https://doi.org/10.1007/s41095-023-0369-x","url":null,"abstract":"<h3>Abstract</h3> Recently, facial-expression recognition (FER) has primarily focused on images in the wild, including factors such as face occlusion and image blurring, rather than laboratory images. Complex field environments have introduced new challenges to FER. To address these challenges, this study proposes a cross-fusion dual-attention network. The network comprises three parts: (1) a cross-fusion grouped dual-attention mechanism to refine local features and obtain global information; (2) a proposed C2 activation function construction method, which is a piecewise cubic polynomial with three degrees of freedom, requiring less computation with improved flexibility and recognition abilities, which can better address slow running speeds and neuron inactivation problems; and (3) a closed-loop operation between the self-attention distillation process and residual connections to suppress redundant information and improve the generalization ability of the model. The recognition accuracies on the RAF-DB, FERPlus, and AffectNet datasets were 92.78%, 92.02%, and 63.58%, respectively. Experiments show that this model can provide more effective solutions for FER tasks. <img alt=\"\" src=\"https://static-content.springer.com/image/MediaObjects/41095_2023_369_Fig1_HTML.jpg\"/> ","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139765951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-task learning and joint refinement between camera localization and object detection 多任务学习以及摄像机定位和物体检测之间的联合改进

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-02-08 DOI: 10.1007/s41095-022-0319-z

Junyi Wang, Yue Qi

{"title":"Multi-task learning and joint refinement between camera localization and object detection","authors":"Junyi Wang, Yue Qi","doi":"10.1007/s41095-022-0319-z","DOIUrl":"https://doi.org/10.1007/s41095-022-0319-z","url":null,"abstract":"Visual localization and object detection both play important roles in various tasks. In many indoor application scenarios where some detected objects have fixed positions, the two techniques work closely together. However, few researchers consider these two tasks simultaneously, because of a lack of datasets and the little attention paid to such environments. In this paper, we explore multi-task network design and joint refinement of detection and localization. To address the dataset problem, we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic process. The dataset provides localization and detection information, and is publicly available at https://drive.google.com/drive/folders/1U28zkuN4_I0dbzkqyIAKlAl5k9oUK0jI?usp=sharing for benchmarking localization and object detection tasks. Targeting this dataset, we have designed a multi-task network, JLDNet, based on YOLO v3, that outputs a target point cloud and object bounding boxes. For dynamic environments, the detection branch also promotes the perception of dynamics. JLDNet includes image feature learning, point feature learning, feature fusion, detection construction, and point cloud regression. Moreover, object-level bundle adjustment is used to further improve localization and detection accuracy. To test JLDNet and compare it to other methods, we have conducted experiments on 7 static scenes, our constructed dataset, and the dynamic TUM RGB-D and Bonn datasets. Our results show state-of-the-art accuracy for both tasks, and the benefit of jointly working on both tasks is demonstrated.\u0000","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139766066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DualSmoke: Sketch-based smoke illustration design with two-stage generative model DualSmoke：基于草图的烟雾插图设计与两阶段生成模型

IF 6.9 3区计算机科学

Computational Visual Media Pub Date : 2024-02-08 DOI: 10.1007/s41095-022-0318-0

Haoran Xie, Keisuke Arihara, Syuhei Sato, Kazunori Miyata

引用次数: 0