Sketch-based 3D Shape Retrieval using Convolutional Neural Networks

TL;DR

This paper introduces a minimalistic view-based approach using Siamese CNNs for sketch-based 3D shape retrieval, eliminating the need for subjective view selection and handcrafted features, resulting in superior performance.

Contribution

It proposes reducing views to two predefined directions and learning features with Siamese CNNs, outperforming state-of-the-art methods in sketch-based 3D shape retrieval.

Findings

Outperforms state-of-the-art in all metrics on three datasets

Reduces complexity by using only two predefined views

Learns features directly from data without manual feature design

Abstract

Retrieving 3D models from 2D human sketches has received considerable attention in the areas of graphics, image retrieval, and computer vision. Almost always in state of the art approaches a large amount of "best views" are computed for 3D models, with the hope that the query sketch matches one of these 2D projections of 3D models using predefined features. We argue that this two stage approach (view selection -- matching) is pragmatic but also problematic because the "best views" are subjective and ambiguous, which makes the matching inputs obscure. This imprecise nature of matching further makes it challenging to choose features manually. Instead of relying on the elusive concept of "best views" and the hand-crafted features, we propose to define our views using a minimalism approach and learn features for both sketches and views. Specifically, we drastically reduce the number of views to only two predefined directions for the whole dataset. Then, we learn two Siamese Convolutional Neural Networks (CNNs), one for the views and one for the sketches. The loss function is defined on the within-domain as well as the cross-domain similarities. Our experiments on three benchmark datasets demonstrate that our method is significantly better than state of the art approaches, and outperforms them in all conventional metrics.