Structure-Aware 3D VR Sketch to 3D Shape Retrieval

TL;DR

This paper introduces a novel approach for 3D shape retrieval from VR sketches by using an adaptive triplet loss based on shape similarity, along with a new dataset of VR sketches, improving retrieval accuracy.

Contribution

It proposes a new adaptive margin triplet loss driven by shape similarity and introduces a VR sketch dataset for 3D shape retrieval tasks.

Findings

Adaptive margin improves retrieval accuracy

Shape similarity under deformations correlates with structural similarity

New VR sketch dataset enhances research in 3D shape retrieval

Abstract

We study the practical task of fine-grained 3D-VR-sketch-based 3D shape retrieval. This task is of particular interest as 2D sketches were shown to be effective queries for 2D images. However, due to the domain gap, it remains hard to achieve strong performance in 3D shape retrieval from 2D sketches. Recent work demonstrated the advantage of 3D VR sketching on this task. In our work, we focus on the challenge caused by inherent inaccuracies in 3D VR sketches. We observe that retrieval results obtained with a triplet loss with a fixed margin value, commonly used for retrieval tasks, contain many irrelevant shapes and often just one or few with a similar structure to the query. To mitigate this problem, we for the first time draw a connection between adaptive margin values and shape similarities. In particular, we propose to use a triplet loss with an adaptive margin value driven by a "fitting gap", which is the similarity of two shapes under structure-preserving deformations. We also conduct a user study which confirms that this fitting gap is indeed a suitable criterion to evaluate the structural similarity of shapes. Furthermore, we introduce a dataset of 202 VR sketches for 202 3D shapes drawn from memory rather than from observation. The code and data are available at https://github.com/Rowl1ng/Structure-Aware-VR-Sketch-Shape-Retrieval.