DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Nisha, Lin, Yizhou, Guo, Jie, Li, Xiu, Lee, Tong-Yee, Yu, Zitong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911687987167232
author Huang, Nisha
Lin, Yizhou
Guo, Jie
Li, Xiu
Lee, Tong-Yee
Yu, Zitong
author_facet Huang, Nisha
Lin, Yizhou
Guo, Jie
Li, Xiu
Lee, Tong-Yee
Yu, Zitong
contents Recently, diffusion-based material transfer methods rely on image fine-tuning or complex architectures with auxiliary networks but face challenges such as text dependency, additional computational costs, and feature misalignment. To address these limitations, we propose \textbf{DealMaTe}, using \underline{\textbf{de}}pth, norm\underline{\textbf{a}}l, and \underline{\textbf{l}}ighting images for \underline{\textbf{ma}}terial \underline{\textbf{t}}ransf\underline{\textbf{e}}r. DealMaTe is a simplified diffusion framework that eliminates text guidance and reference networks. We design a lightweight 3D information injection method, Multi-Dim 3D Shader LoRA, which, without modifying the base model weights, enables compatible control conditions and achieves harmonious and stable results. Additionally, we optimize the attention mechanism with Shader Causal Mutual Attention and key-value (KV) caching to reduce inference latency caused by multiple conditions, improve computational efficiency, and achieve high-quality material transfer results with low architectural complexity. Extensive experiments covering a wide variety of objects and lighting conditions consistently demonstrate that DealMaTe achieves remarkable high-fidelity material transfer under arbitrary input materials. The code is available at https://github.com/haha-lisa/DealMaTe.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15681
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer
Huang, Nisha
Lin, Yizhou
Guo, Jie
Li, Xiu
Lee, Tong-Yee
Yu, Zitong
Graphics
Computer Vision and Pattern Recognition
Recently, diffusion-based material transfer methods rely on image fine-tuning or complex architectures with auxiliary networks but face challenges such as text dependency, additional computational costs, and feature misalignment. To address these limitations, we propose \textbf{DealMaTe}, using \underline{\textbf{de}}pth, norm\underline{\textbf{a}}l, and \underline{\textbf{l}}ighting images for \underline{\textbf{ma}}terial \underline{\textbf{t}}ransf\underline{\textbf{e}}r. DealMaTe is a simplified diffusion framework that eliminates text guidance and reference networks. We design a lightweight 3D information injection method, Multi-Dim 3D Shader LoRA, which, without modifying the base model weights, enables compatible control conditions and achieves harmonious and stable results. Additionally, we optimize the attention mechanism with Shader Causal Mutual Attention and key-value (KV) caching to reduce inference latency caused by multiple conditions, improve computational efficiency, and achieve high-quality material transfer results with low architectural complexity. Extensive experiments covering a wide variety of objects and lighting conditions consistently demonstrate that DealMaTe achieves remarkable high-fidelity material transfer under arbitrary input materials. The code is available at https://github.com/haha-lisa/DealMaTe.
title DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15681