SingleSketch2Mesh : Generating 3D Mesh model from Sketch

TL;DR

SingleSketch2Mesh introduces an AI-based ensemble method using generative networks to convert hand-drawn sketches into 3D mesh models, surpassing existing techniques in accuracy and generalization.

Contribution

It presents a novel ensemble approach leveraging generative networks and encoder-decoder architecture for sketch-to-3D model generation, improving over prior geometric manipulation methods.

Findings

Outperforms existing methods in quantitative evaluation.

Achieves better qualitative results.

Demonstrates generalization to various sketches.

Abstract

Sketching is an important activity in any design process. Designers and stakeholders share their ideas through hand-drawn sketches. These sketches are further used to create 3D models. Current methods to generate 3D models from sketches are either manual or tightly coupled with 3D modeling platforms. Therefore, it requires users to have an experience of sketching on such platform. Moreover, most of the existing approaches are based on geometric manipulation and thus cannot be generalized. We propose a novel AI based ensemble approach, SingleSketch2Mesh, for generating 3D models from hand-drawn sketches. Our approach is based on Generative Networks and Encoder-Decoder Architecture to generate 3D mesh model from a hand-drawn sketch. We evaluate our solution with existing solutions. Our approach outperforms existing approaches on both - quantitative and qualitative evaluation criteria.