EUVIMEDEUVIMED entdecken
Crossref

HiMat: DiT‐based Ultra‐High Resolution SVBRDF Generation

Zixiong Wang, Jian Yang, Yiwei Hu, Miloš Hašan, Beibei Wang

Computer Graphics Forum · 30.03.2026

DOI: 10.1111/cgf.70343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 30.03.2026. Verfasst von Zixiong Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Creating ultra‐high‐resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine‐scale surface details required for close‐up rendering. However, achieving 4K generation faces two key challenges: (1) the need to synthesize multiple reflectance maps at full resolution, which multiplies the pixel budget and imposes prohibitive memory and computational cost, and (2) the requirement to maintain strong pixellevel alignment across maps at 4K, which is particularly difficult when adapting pretrained models designed for the RGB image domain. We introduce HiMat, a diffusion‐based framework tailored for efficient and diverse 4K SVBRDF generation. To address the first challenge, HiMat generates in a high‐compression latent space via a DC‐AE and employs a pretrained diffusion transformer with linear attention to improve per‐map efficiency. To address the second challenge, we propose CrossStitch, a lightweight convolutional module that enforces cross‐map consistency without incurring the cost of global attention. Our experiments show that HiMat achieves high‐fidelity 4K SVBRDF generation with superior efficiency, structural consistency, and diversity compared to prior methods. Beyond materials, our framework also generalizes to related applications such as intrinsic decomposition.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Z., Yang, J., Hu, Y., Hašan, M., & Wang, B. (2026). HiMat: DiT‐based Ultra‐High Resolution SVBRDF Generation. Computer Graphics Forum. https://doi.org/10.1111/cgf.70343

Vancouver

Wang Z, Yang J, Hu Y, Hašan M, Wang B. HiMat: DiT‐based Ultra‐High Resolution SVBRDF Generation. Computer Graphics Forum. 2026. doi:10.1111/cgf.70343

BibTeX
@article{Wang2026,
  author = {Wang, Zixiong and Yang, Jian and Hu, Yiwei and Hašan, Miloš and Wang, Beibei},
  title = {HiMat: DiT‐based Ultra‐High Resolution SVBRDF Generation},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70343}
}
Kostenlos starten →