A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collections

by   David George, et al.

High-level shape understanding and technique evaluation on large repositories of 3D shapes often benefit from additional information known about the shapes. One example of such information is the semantic segmentation of a shape into functional or meaningful parts. Generating accurate segmentations with meaningful segment boundaries is, however, a costly process, typically requiring large amounts of user time to achieve high quality results. In this paper we present an active learning framework for large dataset segmentation, which iteratively provides the user with new predictions by training new models based on already segmented shapes. Our proposed pipeline consists of three novel components. First, we a propose a fast and relatively accurate feature-based deep learning model to provide dataset-wide segmentation predictions. Second, we propose an information theory measure to estimate the prediction quality and for ordering subsequent fast and meaningful shape selection. Our experiments show that such suggestive ordering helps reduce users time and effort, produce high quality predictions, and construct a model that generalizes well. Finally, we provide effective segmentation refinement features to help the user quickly correct any incorrect predictions. We show that our framework is more accurate and in general more efficient than state-of-the-art, for massive dataset segmentation with while also providing consistent segment boundaries.


page 6

page 8

page 9

page 15


iSeg3D: An Interactive 3D Shape Segmentation Tool

A large-scale dataset is essential for learning good features in 3D shap...

Unsupervised Co-segmentation of 3D Shapes via Functional Maps

We present an unsupervised method for co-segmentation of a set of 3D sha...

Informative Path Planning for Active Learning in Aerial Semantic Mapping

Semantic segmentation of aerial imagery is an important tool for mapping...

CoSegNet: Deep Co-Segmentation of 3D Shapes with Group Consistency Loss

We introduce CoSegNet, a deep neural network architecture for co-segment...

MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps

We present a novel region based active learning method for semantic imag...

Importance of Self-Consistency in Active Learning for Semantic Segmentation

We address the task of active learning in the context of semantic segmen...

Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selection

Hierarchies, such as the tree of shapes, are popular representations for...

Please sign up or login with your details

Forgot password? Click here to reset