DeepAI AI Chat
Log In Sign Up

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

05/18/2019
by   Zhizhong Han, et al.
University of Maryland
Tsinghua University
2

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

05/17/2019

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

Learning global features by aggregating information over multiple views ...
05/26/2020

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

Fine-grained 3D shape classification is important and research challengi...
10/22/2020

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

Segmenting arbitrary 3D objects into constituent parts that are structur...
02/05/2023

JPEG Steganalysis Based on Steganographic Feature Enhancement and Graph Attention Learning

The purpose of image steganalysis is to determine whether the carrier im...