M^3ashy: Multi-Modal Material Synthesis via Hyperdiffusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Chenliang, Hu, Zheyuan, Sztrajman, Alejandro, Cai, Yancheng, Liu, Yaru, Oztireli, Cengiz
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911533023363072
author Zhou, Chenliang
Hu, Zheyuan
Sztrajman, Alejandro
Cai, Yancheng
Liu, Yaru
Oztireli, Cengiz
author_facet Zhou, Chenliang
Hu, Zheyuan
Sztrajman, Alejandro
Cai, Yancheng
Liu, Yaru
Oztireli, Cengiz
contents High-quality material synthesis is essential for replicating complex surface properties to create realistic scenes. Despite advances in the generation of material appearance based on analytic models, the synthesis of real-world measured BRDFs remains largely unexplored. To address this challenge, we propose M^3ashy, a novel multi-modal material synthesis framework based on hyperdiffusion. M^3ashy enables high-quality reconstruction of complex real-world materials by leveraging neural fields as a compact continuous representation of BRDFs. Furthermore, our multi-modal conditional hyperdiffusion model allows for flexible material synthesis conditioned on material type, natural language descriptions, or reference images, providing greater user control over material generation. To support future research, we contribute two new material datasets and introduce two BRDF distributional metrics for more rigorous evaluation. We demonstrate the effectiveness of Mashy through extensive experiments, including a novel statistics-based constrained synthesis, which enables the generation of materials of desired categories.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12015
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M^3ashy: Multi-Modal Material Synthesis via Hyperdiffusion
Zhou, Chenliang
Hu, Zheyuan
Sztrajman, Alejandro
Cai, Yancheng
Liu, Yaru
Oztireli, Cengiz
Graphics
High-quality material synthesis is essential for replicating complex surface properties to create realistic scenes. Despite advances in the generation of material appearance based on analytic models, the synthesis of real-world measured BRDFs remains largely unexplored. To address this challenge, we propose M^3ashy, a novel multi-modal material synthesis framework based on hyperdiffusion. M^3ashy enables high-quality reconstruction of complex real-world materials by leveraging neural fields as a compact continuous representation of BRDFs. Furthermore, our multi-modal conditional hyperdiffusion model allows for flexible material synthesis conditioned on material type, natural language descriptions, or reference images, providing greater user control over material generation. To support future research, we contribute two new material datasets and introduce two BRDF distributional metrics for more rigorous evaluation. We demonstrate the effectiveness of Mashy through extensive experiments, including a novel statistics-based constrained synthesis, which enables the generation of materials of desired categories.
title M^3ashy: Multi-Modal Material Synthesis via Hyperdiffusion
topic Graphics
url https://arxiv.org/abs/2411.12015