MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Birsak, Michael, Femiani, John, Zhang, Biao, Wonka, Peter
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913981552132096
author Birsak, Michael
Femiani, John
Zhang, Biao
Wonka, Peter
author_facet Birsak, Michael
Femiani, John
Zhang, Biao
Wonka, Peter
contents Assigning realistic materials to 3D models remains a significant challenge in computer graphics. We propose MatCLIP, a novel method that extracts shape- and lighting-insensitive descriptors of Physically Based Rendering (PBR) materials to assign plausible textures to 3D objects based on images, such as the output of Latent Diffusion Models (LDMs) or photographs. Matching PBR materials to static images is challenging because the PBR representation captures the dynamic appearance of materials under varying viewing angles, shapes, and lighting conditions. By extending an Alpha-CLIP-based model on material renderings across diverse shapes and lighting, and encoding multiple viewing conditions for PBR materials, our approach generates descriptors that bridge the domains of PBR representations with photographs or renderings, including LDM outputs. This enables consistent material assignments without requiring explicit knowledge of material relationships between different parts of an object. MatCLIP achieves a top-1 classification accuracy of 76.6%, outperforming state-of-the-art methods such as PhotoShape and MatAtlas by over 15 percentage points on publicly available datasets. Our method can be used to construct material assignments for 3D shape datasets such as ShapeNet, 3DCoMPaT++, and Objaverse. All code and data will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
Birsak, Michael
Femiani, John
Zhang, Biao
Wonka, Peter
Computer Vision and Pattern Recognition
Graphics
Machine Learning
Assigning realistic materials to 3D models remains a significant challenge in computer graphics. We propose MatCLIP, a novel method that extracts shape- and lighting-insensitive descriptors of Physically Based Rendering (PBR) materials to assign plausible textures to 3D objects based on images, such as the output of Latent Diffusion Models (LDMs) or photographs. Matching PBR materials to static images is challenging because the PBR representation captures the dynamic appearance of materials under varying viewing angles, shapes, and lighting conditions. By extending an Alpha-CLIP-based model on material renderings across diverse shapes and lighting, and encoding multiple viewing conditions for PBR materials, our approach generates descriptors that bridge the domains of PBR representations with photographs or renderings, including LDM outputs. This enables consistent material assignments without requiring explicit knowledge of material relationships between different parts of an object. MatCLIP achieves a top-1 classification accuracy of 76.6%, outperforming state-of-the-art methods such as PhotoShape and MatAtlas by over 15 percentage points on publicly available datasets. Our method can be used to construct material assignments for 3D shape datasets such as ShapeNet, 3DCoMPaT++, and Objaverse. All code and data will be released.
title MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2501.15981