Sketch-based Shape Retrieval using Pyramid-of-Parts

TL;DR

This paper introduces a multi-scale shape descriptor called Pyramid-of-Parts for sketch-based shape retrieval, effectively matching sketches with 3D shapes across scales and outperforming existing methods.

Contribution

It proposes a novel multi-scale shape descriptor that encodes semantic parts and their spatial relationships, enabling improved sketch-to-3D shape retrieval.

Findings

Outperforms state-of-the-art methods in shape retrieval

Works with both manual and automatic sketch segmentation

Effective across multiple scales and shape representations

Abstract

We present a multi-scale approach to sketch-based shape retrieval. It is based on a novel multi-scale shape descriptor called Pyramidof- Parts, which encodes the features and spatial relationship of the semantic parts of query sketches. The same descriptor can also be used to represent 2D projected views of 3D shapes, allowing effective matching of query sketches with 3D shapes across multiple scales. Experimental results show that the proposed method outperforms the state-of-the-art method, whether the sketch segmentation information is obtained manually or automatically by considering each stroke as a semantic part.