Towards 3D VR-Sketch to 3D Shape Retrieval

TL;DR

This paper explores using 3D VR-sketches as an input modality for 3D shape retrieval in virtual reality, introducing new datasets, a synthetic data generation method, and a comparative analysis of retrieval approaches.

Contribution

It introduces a VR utility for sketch collection, a new dataset of VR-sketches, a synthetic data generation method, and demonstrates volumetric approaches outperform multi-view methods for sketch retrieval.

Findings

Volumetric point-based approaches outperform multi-view methods for 3D sketch retrieval.

First dataset of 167 VR-sketches for 3D shape categories from ModelNet.

Synthetic dataset generation enables effective training of deep networks.

Abstract

Growing free online 3D shapes collections dictated research on 3D retrieval. Active debate has however been had on (i) what the best input modality is to trigger retrieval, and (ii) the ultimate usage scenario for such retrieval. In this paper, we offer a different perspective towards answering these questions -- we study the use of 3D sketches as an input modality and advocate a VR-scenario where retrieval is conducted. Thus, the ultimate vision is that users can freely retrieve a 3D model by air-doodling in a VR environment. As a first stab at this new 3D VR-sketch to 3D shape retrieval problem, we make four contributions. First, we code a VR utility to collect 3D VR-sketches and conduct retrieval. Second, we collect the first set of $167$ 3D VR-sketches on two shape categories from ModelNet. Third, we propose a novel approach to generate a synthetic dataset of human-like 3D sketches of different abstract levels to train deep networks. At last, we compare the common multi-view and volumetric approaches: We show that, in contrast to 3D shape to 3D shape retrieval, volumetric point-based approaches exhibit superior performance on 3D sketch to 3D shape retrieval due to the sparse and abstract nature of 3D VR-sketches. We believe these contributions will collectively serve as enablers for future attempts at this problem. The VR interface, code and datasets are available at https://tinyurl.com/3DSketch3DV.