Learning Discriminative 3D Shape Representations By View Discerning Networks

Abstract

In view-based 3D shape recognition, extracting discriminative visual representation of 3D shapes from projected images is considered the core problem. Projections with low discriminative ability can adversely influence the final 3D shape representation. Especially under the real situations with background clutter and object occlusion, the adverse effect is even more severe. To resolve this problem, we propose a novel deep neural network, View Discerning Network, which learns to judge the quality of views and adjust their contributions to the representation of shapes. In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors. These score vectors are used to weight the image features and the weighted features perform much better than original features in 3D shape recognition task. In particular, we introduce two structures of Score Generation Unit, Channel-wise Score Unit and Part-wise Score Unit, to assess the quality of featu

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyleng2018learning

Related papers

• Pvrnet: Point-view Relation Neural Network For 3D Shape Recognition (2018)13.11
• MVTN: Multi-view Transformation Network For 3D Shape Recognition (2020)21.44
• View N-gram Network For 3D Object Retrieval (2019)13.05
• Multiple Discrimination And Pairwise CNN For View-based 3D Object Retrieval (2020)14.27
• Gram Regularization For Multi-view 3D Shape Retrieval (2020)0.00
• Unsupervised Detection Of Distinctive Regions On 3D Shapes (2019)7.50
• Fine-tuned But Zero-shot 3D Shape Sketch View Similarity And Retrieval (2023)5.24
• PREMA: Part-based Recurrent Multi-view Aggregation Network For 3D Shape Retrieval (2021)3.58