Data-Driven Shape Analysis and Processing

TL;DR

This paper reviews data-driven methods for 3D shape analysis, emphasizing their ability to learn from collections of shapes to improve tasks like classification, segmentation, and modeling without relying on hard-coded rules.

Contribution

It provides a comprehensive overview of data-driven shape analysis techniques, highlighting their main concepts, applications, and potential future research directions.

Findings

Data-driven methods improve shape classification and segmentation.

Learning models can reason about shape properties without explicit programming.

The review compares qualitative and numerical results across techniques.

Abstract

Data-driven methods play an increasingly important role in discovering geometric, structural, and semantic relationships between 3D shapes in collections, and applying this analysis to support intelligent modeling, editing, and visualization of geometric data. In contrast to traditional approaches, a key feature of data-driven approaches is that they aggregate information from a collection of shapes to improve the analysis and processing of individual shapes. In addition, they are able to learn models that reason about properties and relationships of shapes without relying on hard-coded rules or explicitly programmed instructions. We provide an overview of the main concepts and components of these techniques, and discuss their application to shape classification, segmentation, matching, reconstruction, modeling and exploration, as well as scene analysis and synthesis, through reviewing the literature and relating the existing works with both qualitative and numerical comparisons. We conclude our report with ideas that can inspire future research in data-driven shape analysis and processing.