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

2026-03-18

AI Summary

This work addresses the inefficiency of manually assigning materials to geometrically diverse yet materially homogeneous repetitive parts in textureless meshes. We propose the first material-aware 3D part grouping method, enabling users to select a single part and automatically retrieve other parts sharing the same material. To this end, we introduce the first benchmark dataset comprising 100 models and 241 queries, and design a material-aware embedding mechanism that fuses local geometric features with global contextual information. A part encoder, trained via supervised contrastive learning, optimizes the embedding space for efficient nearest-neighbor retrieval. Experiments demonstrate that our approach significantly outperforms baseline methods in both accuracy and efficiency. The method has been integrated into an interactive tool, substantially accelerating material assignment workflows for artists.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Matrix & Tensor Methods

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• material-aware grouping
• untextured meshes
• 3D part segmentation
• repeated structures
• material assignment

Innovation

• material-aware grouping
• 3D part embedding
• contrastive learning
• untexured meshes
• interactive material assignment