PVCLN: Point-View Complementary Learning Network for 3D Shape Recognition

Sun, Sumei; Li, Yun; Ren, Minjie; Guo, Li; Yao, Xing

doi:10.1109/access.2020.3047820

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the effectiveness of our method, we conduct extensive experiments on two commonly used image‐based 3D model retrieval datasets, namely MI3DOR 34 and MI3DOR‐2 10 . The MI3DOR dataset has 21 classes with 21,000 2D images and 7690 3D models, where 2D images are selected from ImageNet dataset 35 and 3D models are selected from datasets like PSB, 36 NTU, 37 ModelNet40, 38 and ShapeNetCore55 39 . The MI3DOR‐2 dataset has 40 classes with 18,694 2D images and 3982 3D models, which are from Google website and ModelNet40 dataset respectively.…”

Section: Methodsmentioning

confidence: 99%

Source‐enhanced prototypical alignment for single image 3D model retrieval

Song

Wang

Zhang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Single image 3D model retrieval has attracted a lot of attentions with the convenience of organizing large-scale unlabeled 3D models. Existing methods transfer the knowledge from well-annotated 2D images (i.e., source domain) to unlabeled 3D models (i.e., target domain) to improve the discriminability of 3D models and align the feature distributions of 2D images and 3D models. However, during the alignment, the feature learning target of improving the discriminability of 3D models sometimes confuses the boundaries between 2D image categories, where prior methods ignore keeping the discriminability of 2D images. Motivated by this observation, we propose a source-enhanced prototypical alignment framework to first remain the discriminability of 2D images and then guide the category-level cross-domain alignment with better image representations. Specifically, a novel separation and compactness loss is proposed for images to separate the samples from different categories and compact the samples within the same category. Then we perform prototypical alignment to make 2D image features assist in the discriminative feature learning for 3D models. We evaluate the proposed method on the commonly used cross-domain 3D model retrieval benchmarks, namely MI3DOR and MI3DOR-2, and the results demonstrate the effectiveness of the proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

Source‐enhanced prototypical alignment for single image 3D model retrieval

Song

Wang

Zhang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

Hierarchical deep semantic alignment for cross-domain 3D model retrieval

Song

Yang

et al. 2023

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

PVFAN: Point-view fusion attention network for 3D shape recognition

Cao,

Liao

2023

IFS

View full text Add to dashboard Cite

3D shape recognition is a critical research topic in the field of computer vision, attracting substantial attention. Existing approaches mainly focus on extracting distinctive 3D shape features; however, they often neglect the model’s robustness and lack refinement in deep features. To address these limitations, we propose the point-view fusion attention network that aims to extract a concise, informative, and robust 3D shape descriptor. Initially, our approach combines multi-view features with point cloud features to obtain accurate and distinguishable fusion features. To effectively handle these fusion features, we design a dual-attention convolutional network which consists of a channel attention module and a spatial attention module. This dual-attention mechanism greatly enhances the generalization ability and robustness of 3D recognition models. Notably, we introduce a strip-pooling layer in the channel attention module to refine the features, resulting in improved fusion features that are more compact. Finally, a classification process is performed on the refined features to assign appropriate 3D shape labels. Our extensive experiments on the ModelNet10 and ModelNet40 datasets for 3D shape recognition and retrieval demonstrate the remarkable accuracy and robustness of the proposed method.

show abstract

PVCLN: Point-View Complementary Learning Network for 3D Shape Recognition

Cited by 3 publications

References 24 publications

Source‐enhanced prototypical alignment for single image 3D model retrieval

Source‐enhanced prototypical alignment for single image 3D model retrieval

Hierarchical deep semantic alignment for cross-domain 3D model retrieval

PVFAN: Point-view fusion attention network for 3D shape recognition

Contact Info

Product

Resources

About