检索结果-内蒙古大学图书馆

S²Mix: Style and Semantic Mix for cross-domain 3d model retrieval

JOURNAL OF VISUAL COMMUNICATION ANd IMAGE REPRESENTATION 2025年 107卷

作者： Fu, Xinwei Song, dan Yang, Yue Zhang, Yuyi Wang, Bo Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Hisense State Key Lab Digital Multimedia Technol Qingdao Peoples R China

With the development of deep neural networks and image processing technology, cross-domain 3d model retrieval algorithms based on 2d images have attracted much attention, utilizing visual information from labeled 2d images to assist in processing unlabeled 3d models. Existing unsupervised cross-domain 3d model retrieval algorithm use domain adaptation to narrow the modality gap between 2d images and 3d models. However, these methods overlook specific style visual information between different domains of 2d images and 3d models, which is crucial for reducing the domain distribution discrepancy. To address this issue, this paper proposes a Style and Semantic Mix (S2Mix) network for cross-domain 3d model retrieval, which fuses style visual information and semantic consistency features between different domains. Specifically, we design a style mix module to perform on shallow feature maps that are closer to the input data, learning 2d image and 3d model features with intermediate domain mixed style to narrow the domain distribution discrepancy. In addition, in order to improve the semantic prediction accuracy of unlabeled samples, a semantic mix module is also designed to operate on deep features, fusing features from reliable unlabeled 3d model and 2d image samples with semantic consistency. Our experiments demonstrate the effectiveness of the proposed S2Mixon two commonly-used cross-domain 3d model retrieval datasets MI3dOR-1 and MI3dOR-2.

关键词： 3d model retrieval Image style transfer Unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Adaptive CLIP for open-domain 3d model retrieval

引用

INFORMATION PROCESSING & MANAGEMENT 2025年第2期62卷

作者： Song, dan Qiang, Zekai Zhang, Chumeng Wang, Lanjun Liu, Qiong Yang, You Liu, An-An Tianjin Univ Sch Elect & Informat Engn Tianjin 300110 Peoples R China Tianjin Univ Sch New Media & Commun Tianjin 300110 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China

In order to effectively enhance the practicality of 3d model retrieval, we adopt a single real image as the query sample for retrieving 3d models. However, the significant differences between 2d images and 3d models in terms of lighting conditions, textures and backgrounds, posing a great challenge for accurate retrieval. Existing work on 3d model retrieval mainly focuses on closed-domain research, while the open-domain condition where the category relationship between the query image and the 3d model is unknown is more in line with the needs of real scenarios. CLIP shows significant promise in comprehending open-world visual concepts, facilitating effective zero-shot image recognition. Based on this multimodal pre-training large language model, we introduce Adaptive Open-domain Semantic Nearest-neighbor Contrast (AOSNC), a method for learning and aligning multi-modal text, image, and 3d model. In order to solve the issue of inconsistent cross-domain categories and difficult sample correlation in open-domain, we construct a cross-modal bridge using CLIP. This model utilizes textual features to bridge the gap between 2d images and 3d model views. Additionally, we design an adaptive network layer to address the limitations of the pre-training model for 3d model views and enhance cross-modal alignment. We propose a mutual nearest-neighbor semantic alignment loss to address the challenge of aligning features from disparate modalities (text, images, and 3d models). This loss function enhances cross-modal learning by effectively associating and distinguishing features, improving retrieval accuracy. We conducted comprehensive experiments using the image-based 3d model retrieval dataset MI3dOR and the cross-domain 3d model retrieval dataset NTU-PSB to validate the superiority of the proposed method. Our results show significant improvements in several evaluation metrics, underscoring the efficacy of our method in augmenting cross-modal feature alignment and retrieval perfor

关键词： 3d model retrieval Open-domain retrieval Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

dual-Stage Uncertainty modeling for Unsupervised Cross-domain 3d model retrieval

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2024年 26卷 8996-9007页

作者： Li, Wenhui Zhou, Houran Zhang, Chenyu Nie, Weizhi Li, Xuanya Liu, An-An Tianjin Univ Tianjin 300072 Peoples R China Baidu Inc Beijing 100089 Peoples R China

Unsupervised cross-domain 3d model retrieval aims to retrieve unlabeled 3d models (target domain) using labeled 2d images (source domain). domain adaptation approaches have shown impressive performance for cross-domain 3d model retrieval. However, conventional methods typically represent samples from different domains as deterministic points, overlooking the diversity in sample characteristics and relationships. These approaches lead to challenges in achieving a robust representation of both samples and categories. To address above challenges, we propose a dual-stage uncertainty modeling (dSUM) for unsupervised cross-domain 3d model retrieval, which utilizes Gaussian distribution to effectively model the uncertainty characteristics in both sample and class and obtain the robust and domain-invariant representations. Specifically, in the multi-view uncertainty encoding stage, we discard the conventional pooling operations and utilize the uncertainty modeling among multiple views to fuse the common and specific information of 2d images and 3d models. In the cross-domain feature alignment stage, we adopt the Gaussian distribution of samples belonging to the same category, which can well maintain the sample diversity as well as facilitate to eliminate the domain discrepancy. Our method achieves improvements of 2.61% and 2.65% in terms of FT on two cross-domain datasets, respectively, verifying its superiority through extensive qualitative and quantitative experiments.

关键词： Solid modeling Uncertainty Three-dimensional displays Semantics Prototypes Gaussian distribution Bicycles Cross-domain learning 3d model retrieval uncertainty encoding domain adaptation

来源：评论

学校读者我要写书评

暂无评论

domain-specific modeling and semantic alignment for image-based 3d model retrieval

引用

COMPUTERS & GRAPHICS-UK 2023年第1期115卷 25-34页

作者： Song, dan Jiang, Xue-Jing Zhang, Yue Zhang, Fang-Lue Jin, Yao Zhang, Yun Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Univ Sci & Technol China Sch Biomed Engn Div Life Sci & Med Hefei Peoples R China Univ Sci & Technol China Suzhou Inst Adv Res Ctr Med Imaging Robot Analyt Comp & Learning MIRAC Suzhou Peoples R China Victoria Univ Wellington Sch Engn & Comp Sci Wellington New Zealand Zhejiang Sci Tech Univ Sch Comp Sci & Technol Sch Artificial Intelligence Hangzhou Peoples R China Commun Univ Zhejiang Coll Media Engn Hangzhou Peoples R China

Image-based 3d model retrieval aims to search for 3d models according to 2d image queries, which provides a convenient way for the management of large 3d model datasets. Most of the related works put the emphasis on bridging the modality gap between 2d images and 3d models, which faces a lot of challenges due to the huge domain discrepancy. In this paper, we explicitly model and eliminate the domain-specific features of 2d images and 3d models. To alleviate the negative effect of complex background of natural images, we adopt semantic focus loss to constrain networks to learn the most semantically relevant feature representations for both 2d images and 3d models. We conduct extensive experiments on two cross-domain 3d model retrieval datasets, MI3dOR and MI3dOR-2, to show the effectiveness of the proposed method.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： 3d model retrieval domain adaptation Semantic alignment

来源：评论

学校读者我要写书评

暂无评论

Focus on Hard Samples: Hierarchical Unbiased Constraints for Cross-domain 3d model retrieval

引用

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2023年第11期33卷 7036-7049页

作者： Li, Tian-Bao Liu, An-An Song, dan Li, Wen-Hui Li, Xuan-Ya Su, Yu-Ting Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Inst Artificial Intelligence Hefei Comprehens Natl Sci Ctr Hefei 230026 Peoples R China Baidu Inc Beijing 100105 Peoples R China

Cross-domain 3d model retrieval facilitates the management of explosively emerging unlabeled 3d models with conveniently available 2d images or RGB-d objects, which has attracted more and more attention. The modality gap between query samples (2d images or RGB-d objects) and 3d models makes the task challenging, and adversarial domain adaptation techniques have achieved success in narrowing such gaps. However, existing methods always pay excessive attention to the samples with high discriminability and transferability, whereas the hard samples with rich information are neglected. Accordingly, we propose hierarchical unbiased constraints to make full use of data at semantic level, sample level and feature level to improve the retrieval performance. At semantic level, we utilize maximum F-norm loss to constrain the semantic prediction results of target domain, which takes advantage of more hard samples to reduce ambiguous predictions and enhance discriminability. At sample level, we propose an adaptive triplet center loss to assign less confident samples with a farther negative class, which reliably compacts samples within the same class and expands the distance across different classes. At feature level, we perform SVd (singular value decomposition) for both source features and target features and suppress the relative value of the largest singular value, so that the information of other eigenvectors can be fully utilized to improve transferability. Experiments on two public datasets validate the superiority of the proposed method, and the ablation study analyzes different roles played by these hierarchical unbiased constraints.

关键词： 3d model retrieval domain adaptation 3d data management

来源：评论

学校读者我要写书评

暂无评论

Learning Transferable and discriminative Representations for 2d Image-Based 3d model retrieval

引用

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2022年第10期32卷 7147-7159页

作者： Zhou, Yaqian Liu, Yu Zhou, Heyu Cheng, Zhiyong Li, Xuanya Liu, An-An Tianjin Univ Sch Microelect Tianjin 300072 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230088 Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Qilu Univ Technol Shandong Acad Sci Shandong Artificial Intelligence Inst Jinan 250014 Peoples R China Baidu Inc Beijing 100105 Peoples R China

Existing research on the 2d image-based 3d model retrieval task focuses on learning transferable representations directly to narrow the domain discrepancy. However, it is not easy to achieve in practice due to the significant variations across two domains. In addition, some methods design a domain discriminator to distinguish the feature arising from source or target domains for transferable feature representations learning, which will lead to an unexpected deterioration of the feature discriminability. To settle these problems, we propose jointly learning transferable and discriminative representations for 2d image-based 3d model retrieval. Specifically, we extract features from the 2d images and 3d models (described as multiple views) by CNN. Considering the difficulty of directly narrowing the discrepancy of two domains, we are prone to connect 2d image and 3d model domains to an intermediate domain, where the domain gap aims to be eliminated. However, the feature transferability does not denote well discriminability. Based on the batch spectral penalization (BSP) theory, the feature transferability is dominated by feature vectors with higher singular values, while the feature discriminability depends on more eigenvectors with lower singular values to convey rich discriminative structures. Therefore, we penalize the largest singular values so that the feature vectors with lower singular values are appropriately enhanced, thereby strengthening feature discriminability. A series of experiments on two challenging datasets, MI3dOR and MI3dOR-2, indicate that our method can significantly improve performance.

关键词： Three-dimensional displays Solid modeling Adaptation models Feature extraction Error analysis data models Generative adversarial networks 3d model retrieval unsupervised domain adaptation multi-view

来源：评论

学校读者我要写书评

暂无评论

Research on 3d model retrieval Technology Based on Audio Fingerprint and Contour View 14th

Research on 3D Model Retrieval Technology Based on Audio Fin...

引用

14th International Workshop of Advanced Manufacturing and Automation, IWAMA 2024

作者： Lv, Yingshou Zhou, Chuanhong Ma, Chuanqi School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (纸本)9789819626243

With the sustained development of CAd technology in the field of mechanical design, the volume of three-dimensional (3d) CAd model data has been growing exponentially. To meet the challenge of rapidly increasing 3d model repositories in the mechanical industry and the demand for efficient retrieval, this paper proposes a 3d model retrieval algorithm based on audio fingerprints and contour views for STL format 3d models. The aim is to provide mechanical designers with an efficient and accurate method of retrieving the required parts from the vast model repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3d model retrieval Audio fingerprint extraction Contour view Rotational normalization

来源：评论

学校读者我要写书评

暂无评论

Multi-view 3d model retrieval based on enhanced detail features with contrastive center loss

引用

MULTIMEdIA TOOLS ANd APPLICATIONS 2022年第8期81卷 10407-10426页

作者： Chen, Qiang Chen, Yinong Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China Arizona State Univ Sch Comp & Augmented Intelligence Tempe AZ 85281 USA

In recent years, 3d model retrieval has become a hot topic. With the development of deep learning technology, many state-of-the-art deep learning based multi-view 3d model retrieval algorithms have emerged. One of the major challenges in view-based 3d model retrieval is how to achieve rotation invariant. MVCNN (Multi-View Convolutional Neural Networks) achieving higher performance while maintaining rotation invariant. However, the element-wise maximum operation across the views leads to the loss of detailed information. To address this problem, in this paper, we use a deep cross-modal learning method to treat the features of different views as different modal features. First, we select two of the views as the input of the deep multimodal learning method. Then we combine the proposed method with an improved contrastive center loss, so that we can align the features in the same subspace and obtain a higher discriminative fused feature. Experimental results show that the training of the proposed CNN (Convolutional Neural Networks) model is based on the existing MVCNN pre-trained model, which takes only 18 epochs to converge, and it obtains 90.07% in terms of mAP (mean average precision) using only the MVCNN as the backbone, which is comparable to the feature fusion algorithm PVRNet (Point-View Relation Neural Network) and much higher than the mAP of MVCNN (80.2%). The experimental results demonstrated that the proposed method avoids explicitly learning the weights for fusion of different view features, while incorporating more details into the 3d model's final descriptor can improve the retrieval results.

关键词： 3d model retrieval Multi-view deep features Contrastive center loss Enhanced detail features deep cross-modal

来源：评论

学校读者我要写书评

暂无评论

Sequential learning for sketch-based 3d model retrieval

引用

MULTIMEdIA SYSTEMS 2022年第3期28卷 761-778页

作者： Yang, Hairui Tian, Yu Yang, Caifei Wang, Zhihui Wang, Lei Li, Haojie Dalian Univ Technol Sch Software Technol Dalian Peoples R China Dalian Univ Technol Ritsumeikan Univ Int Sch Informat Sci & Engn Dalian Peoples R China

Sketch-based 3d model retrieval suffers large visual discrepancy between 3d models and 2d sketches. Most existing methods directly project samples from both modalities into a same semantic embedding space to alleviate the discrepancy. We argue that simultaneous learning of those two modalities would restrict the discrimination of 3d model representation, resulting in inferior retrieval results. In this work, we propose a novel sequential learning (SL) framework for sketch-based 3d model retrieval to learn 3d model representation and 2d sketch representation separately and sequentially. Specifically, the SL framework is composed of two modules, 3d model network (3dMN) and 2d sketch network (2dSN). Firstly, we train 3dMN with a discriminative loss formulated only on 3d models to promote discrimination. Then, the learned representations of 3d models guide 2dSN to learn discriminative 2d sketch representations. In the second phase, we further mine the implicit fine-grained class information of 3d models by unsupervised clustering algorithms. An alignment loss is formulated on 2d sketches and corresponding fine-grained class centers of 3d models. Extensive experiments on three large-scale benchmark datasets for 3d model retrieval validate the efficacy of the proposed SL framework and fine-grained class representations.

关键词： Sketch-based retrieval 3d model retrieval Sequential learning Shape representation

来源：评论

学校读者我要写书评

暂无评论

Joint Local Correlation and Global Contextual Information for Unsupervised 3d model retrieval and Classification

引用

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2022年第5期32卷 3265-3278页

作者： Li, Wenhui Zhao, Zhenlan Liu, An-An Gao, Zan Yan, Chenggang Mao, Zhendong Chen, Haipeng Nie, Weizhi Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Chinese Acad Sci Key Lab Electromagnet Space Informat Beijing 100864 Peoples R China Qilu Univ Technol Shandong Artificial Intelligence Inst Shandong Acad Sci Jinan 250353 Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230052 Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

Unsupervised 3d model analysis has attracted tremendous attentions with the increasing growth of 3d model data and the extensive human annotations. Many effective methods have been designed to address the 3d model analysis with labeled information, while rare methods devote to unsupervised deep learning due to the difficulty of mining reliable information. In this paper, we propose a novel unsupervised deep learning method named joint local correlation and global contextual information (LCGC) for 3d model retrieval and classification, which mines the reliable triplet set and uses triplet loss to optimize the deep neural network. Our method proposes two schemes: 1) Local self-correlation information learning, which adopts the intra and inter information to construct the view-level triplet set. 2) Global neighbor contextual information learning, which employs the neighbor contextual information to explore the reliable relations among 3d models and construct the model-level triplet set. The above schemes encourage that the selected triple set can been used to improve the discrimination of learned features. Extensive evaluations on two large-scale datasets, modelNet40 and ShapeNet55, have demonstrated the effectiveness of our proposed method.

关键词： Three-dimensional displays Solid modeling Context modeling data models Analytical models deep learning Feature extraction 3d model retrieval 3d model classification unsupervised feature learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：