Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views

by   Zhizhong Han, et al.

Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute low-level features for entire views without considering part-level information. In contrast, we propose a deep neural network, called Parts4Feature, to learn 3D global features from part-level information in multiple views. We introduce a novel definition of generally semantic parts, which Parts4Feature learns to detect in multiple views from different 3D shape segmentation benchmarks. A key idea of our architecture is that it transfers the ability to detect semantically meaningful parts in multiple views to learn 3D global features. Parts4Feature achieves this by combining a local part detection branch and a global feature learning branch with a shared region proposal module. The global feature learning branch aggregates the detected parts in terms of learned part patterns with a novel multi-attention mechanism, while the region proposal module enables locally and globally discriminative information to be promoted by each other. We demonstrate that Parts4Feature outperforms the state-of-the-art under three large-scale 3D shape benchmarks.


page 1

page 2

page 3

page 4

page 5

page 6

page 7


3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

Learning global features by aggregating information over multiple views ...

Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

Fine-grained 3D shape classification is important and research challengi...

ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences

3D shape captioning is a challenging application in 3D shape understandi...

SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

Segmenting arbitrary 3D objects into constituent parts that are structur...

Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

Unsupervised learning of global features for 3D shape analysis is an imp...

DFR-Net: Density Feature Refinement Network for Image Dehazing Utilizing Haze Density Difference

In image dehazing task, haze density is a key feature and affects the pe...

Please sign up or login with your details

Forgot password? Click here to reset