Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes

TL;DR

This paper presents Material Magic Wand, a tool for automatically grouping 3D mesh parts by material using a learned embedding, simplifying the process of material assignment in untextured meshes.

Contribution

It introduces a novel material-aware part embedding method trained with contrastive loss, enabling automatic grouping of mesh parts sharing the same material.

Findings

Effective in retrieving material-consistent parts

Reduces manual effort in material assignment

Validated on a new curated dataset

Abstract

We introduce the problem of material-aware part grouping in untextured meshes. Many real-world shapes, such as scales of pinecones or windows of buildings, contain repeated structures that share the same material but exhibit geometric variations. When assigning materials to such meshes, these repeated parts often require piece-by-piece manual identification and selection, which is tedious and time-consuming. To address this, we propose Material Magic Wand, a tool that allows artists to select part groups based on their estimated material properties -- when one part is selected, our algorithm automatically retrieves all other parts likely to share the same material. The key component of our approach is a part encoder that generates a material-aware embedding for each 3D part, accounting for both local geometry and global context. We train our model with a supervised contrastive loss that brings embeddings of material-consistent parts closer while separating those of different materials; therefore, part grouping can be achieved by retrieving embeddings that are close to the embedding of the selected part. To benchmark this task, we introduce a curated dataset of 100 shapes with 241 part-level queries. We verify the effectiveness of our method through extensive experiments and demonstrate its practical value in an interactive material assignment application.