Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.15660 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913131993759744 |
|---|---|
| author | Huang, Nisha Liu, Henglin Lin, Yizhou Huang, Kaer Chen, Chubin Guo, Jie Lee, Tong-Yee Li, Xiu |
| author_facet | Huang, Nisha Liu, Henglin Lin, Yizhou Huang, Kaer Chen, Chubin Guo, Jie Lee, Tong-Yee Li, Xiu |
| contents | Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extra computational costs, and feature misalignment. To address these limitations, we propose MaTe, a streamlined diffusion framework that eliminates textual guidance and reference networks. MaTe integrates input images at the token level, enabling unified processing via multi-modal attention in a shared latent space. This design removes the need for additional adapters, ControlNet, inversion sampling, or model fine-tuning. Extensive experiments demonstrate that MaTe achieves high-quality material generation under a zero-shot, training-free paradigm. It outperforms state-of-the-art methods in both visual quality and efficiency while preserving precise detail alignment, significantly simplifying inference prerequisites. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15660 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer Huang, Nisha Liu, Henglin Lin, Yizhou Huang, Kaer Chen, Chubin Guo, Jie Lee, Tong-Yee Li, Xiu Computer Vision and Pattern Recognition Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extra computational costs, and feature misalignment. To address these limitations, we propose MaTe, a streamlined diffusion framework that eliminates textual guidance and reference networks. MaTe integrates input images at the token level, enabling unified processing via multi-modal attention in a shared latent space. This design removes the need for additional adapters, ControlNet, inversion sampling, or model fine-tuning. Extensive experiments demonstrate that MaTe achieves high-quality material generation under a zero-shot, training-free paradigm. It outperforms state-of-the-art methods in both visual quality and efficiency while preserving precise detail alignment, significantly simplifying inference prerequisites. |
| title | MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.15660 |