Freehand Sketch Generation from Mechanical Components

TL;DR

This paper introduces MSFormer, a novel two-stage generative framework that produces humanoid freehand sketches of mechanical components, enhancing data-driven engineering modeling with improved realism and robustness.

Contribution

We propose MSFormer, the first framework to generate humanoid freehand mechanical sketches using multi-view contour extraction and transformer-based translation.

Findings

Achieves state-of-the-art performance in freehand mechanical sketch generation.

Effectively captures human-like sketching style and stroke distribution.

Demonstrates robustness and generalizability across various mechanical components.

Abstract

Drawing freehand sketches of mechanical components on multimedia devices for AI-based engineering modeling has become a new trend. However, its development is being impeded because existing works cannot produce suitable sketches for data-driven research. These works either generate sketches lacking a freehand style or utilize generative models not originally designed for this task resulting in poor effectiveness. To address this issue, we design a two-stage generative framework mimicking the human sketching behavior pattern, called MSFormer, which is the first time to produce humanoid freehand sketches tailored for mechanical components. The first stage employs Open CASCADE technology to obtain multi-view contour sketches from mechanical components, filtering perturbing signals for the ensuing generation process. Meanwhile, we design a view selector to simulate viewpoint selection tasks during human sketching for picking out information-rich sketches. The second stage translates contour sketches into freehand sketches by a transformer-based generator. To retain essential modeling features as much as possible and rationalize stroke distribution, we introduce a novel edge-constraint stroke initialization. Furthermore, we utilize a CLIP vision encoder and a new loss function incorporating the Hausdorff distance to enhance the generalizability and robustness of the model. Extensive experiments demonstrate that our approach achieves state-of-the-art performance for generating freehand sketches in the mechanical domain. Project page: https://mcfreeskegen.github.io .